Model save
Browse files- README.md +67 -0
- all_results.json +9 -0
- generation_config.json +6 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +346 -0
- runs/Jun10_06-28-29_action-graph-trainer/events.out.tfevents.1718000933.action-graph-trainer.4056328.0 +2 -2
- train_results.json +9 -0
- trainer_state.json +1382 -0
README.md
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: Qwen/Qwen2-7B
|
4 |
+
tags:
|
5 |
+
- trl
|
6 |
+
- sft
|
7 |
+
- generated_from_trainer
|
8 |
+
datasets:
|
9 |
+
- generator
|
10 |
+
model-index:
|
11 |
+
- name: zephyr-qwen2-7b-sft
|
12 |
+
results: []
|
13 |
+
---
|
14 |
+
|
15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
+
should probably proofread and complete it, then remove this comment. -->
|
17 |
+
|
18 |
+
# zephyr-qwen2-7b-sft
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [Qwen/Qwen2-7B](https://huggingface.co/Qwen/Qwen2-7B) on the generator dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 1.0646
|
23 |
+
|
24 |
+
## Model description
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Intended uses & limitations
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training and evaluation data
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training procedure
|
37 |
+
|
38 |
+
### Training hyperparameters
|
39 |
+
|
40 |
+
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 2e-05
|
42 |
+
- train_batch_size: 8
|
43 |
+
- eval_batch_size: 8
|
44 |
+
- seed: 42
|
45 |
+
- distributed_type: multi-GPU
|
46 |
+
- num_devices: 8
|
47 |
+
- gradient_accumulation_steps: 2
|
48 |
+
- total_train_batch_size: 128
|
49 |
+
- total_eval_batch_size: 64
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: cosine
|
52 |
+
- lr_scheduler_warmup_ratio: 0.1
|
53 |
+
- num_epochs: 1
|
54 |
+
|
55 |
+
### Training results
|
56 |
+
|
57 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
58 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
59 |
+
| 1.0626 | 1.0 | 956 | 1.0646 |
|
60 |
+
|
61 |
+
|
62 |
+
### Framework versions
|
63 |
+
|
64 |
+
- Transformers 4.40.2
|
65 |
+
- Pytorch 2.3.0+cu121
|
66 |
+
- Datasets 2.19.1
|
67 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"total_flos": 500925122740224.0,
|
4 |
+
"train_loss": 1.0766646904426638,
|
5 |
+
"train_runtime": 10839.8443,
|
6 |
+
"train_samples": 207864,
|
7 |
+
"train_samples_per_second": 11.286,
|
8 |
+
"train_steps_per_second": 0.088
|
9 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 151643,
|
3 |
+
"eos_token_id": 151643,
|
4 |
+
"max_new_tokens": 2048,
|
5 |
+
"transformers_version": "4.40.2"
|
6 |
+
}
|
model-00001-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f6039494ac641d99d13b6f028d2a309d117292be0301ad9e77ccb61d5d09d61
|
3 |
+
size 4877660776
|
model-00002-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7907147daaa9fad1b0dd1ccd01bf743294c785fed19b77a288ef3e6cbe91768a
|
3 |
+
size 4932751008
|
model-00003-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bea1812025c1808c2ebc632f73cad6038809c45373791f1789cf32259447d9d4
|
3 |
+
size 4330865200
|
model-00004-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3f1bf1dbca8a6fa54c435b5dee8ee34b090850ba9b780c8d6f3083db9d29355
|
3 |
+
size 1089994880
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,346 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 15231233024
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "model-00004-of-00004.safetensors",
|
7 |
+
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
13 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
14 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
15 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
16 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
17 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
18 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
19 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
20 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
21 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
22 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
23 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
24 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
25 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
26 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
27 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
28 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
29 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
30 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
31 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
32 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
33 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
34 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
35 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
36 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
37 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
38 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
39 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
40 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
41 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
42 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
43 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
44 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
45 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
46 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
47 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
48 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
49 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
50 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
51 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
52 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
53 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
54 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
55 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
56 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
57 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
58 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
59 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
60 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
61 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
62 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
63 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
64 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
65 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
66 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
67 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
68 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
69 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
70 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
71 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
72 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
73 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
74 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
75 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
76 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
77 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
78 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
79 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
80 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
81 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
82 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
83 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
84 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
85 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
86 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
87 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
88 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
89 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
90 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
91 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
92 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
93 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
94 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
95 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
96 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
97 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
98 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
99 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
100 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
101 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
102 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
103 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
104 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
105 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
106 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
107 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
108 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
109 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
110 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
111 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
112 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
113 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
114 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
115 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
116 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
117 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
118 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
119 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
120 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
121 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
122 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
123 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
124 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
125 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
126 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
127 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
128 |
+
"model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
129 |
+
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
130 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
131 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
132 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
133 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
134 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
135 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
136 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
137 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
138 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
139 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
140 |
+
"model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
141 |
+
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
142 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
143 |
+
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
144 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
145 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
146 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
147 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
148 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
149 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
150 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
151 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
152 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
153 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
154 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
155 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
156 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
157 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
158 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
159 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
160 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
161 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
162 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
163 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
164 |
+
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
165 |
+
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
166 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
167 |
+
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
168 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
169 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
170 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
171 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
172 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
173 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
174 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
175 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
176 |
+
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
177 |
+
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
178 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
179 |
+
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
180 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
181 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
182 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
183 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
184 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
185 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
186 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
187 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
188 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
189 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
190 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
191 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
192 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
193 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
194 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
195 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
196 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
197 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
198 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
199 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
200 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
201 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
202 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
203 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
204 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
205 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
206 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
207 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
208 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
209 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
210 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
211 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
212 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
213 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
214 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
215 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
216 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
217 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
218 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
219 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
220 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
221 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
222 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
223 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
224 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
225 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
226 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
227 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
228 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
229 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
230 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
231 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
232 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
233 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
234 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
235 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
236 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
237 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
238 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
239 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
240 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
241 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
242 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
243 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
244 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
245 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
246 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
247 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
248 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
249 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
250 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
251 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
252 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
253 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
254 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
255 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
256 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
257 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
258 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
259 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
260 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
261 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
262 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
263 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
264 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
265 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
266 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
267 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
268 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
269 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
270 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
271 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
272 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
273 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
274 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
275 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
276 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
277 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
278 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
279 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
280 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
281 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
282 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
283 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
284 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
285 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
286 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
287 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
288 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
289 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
290 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
291 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
292 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
293 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
294 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
295 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
296 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
297 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
298 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
299 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
300 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
301 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
302 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
303 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
304 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
305 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
306 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
307 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
308 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
309 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
310 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
311 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
312 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
313 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
314 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
315 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
316 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
317 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
318 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
319 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
320 |
+
"model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
321 |
+
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
322 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
323 |
+
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
324 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
325 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
326 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
327 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
328 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
329 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
330 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
331 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
332 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
333 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
334 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
335 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
336 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
337 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
338 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
339 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
340 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
341 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
342 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
343 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
344 |
+
"model.norm.weight": "model-00003-of-00004.safetensors"
|
345 |
+
}
|
346 |
+
}
|
runs/Jun10_06-28-29_action-graph-trainer/events.out.tfevents.1718000933.action-graph-trainer.4056328.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:080a20ece6e0a5f501a0fdfabe67f8205f0d32ba274fea1708f7e41a1e0a098f
|
3 |
+
size 45881
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"total_flos": 500925122740224.0,
|
4 |
+
"train_loss": 1.0766646904426638,
|
5 |
+
"train_runtime": 10839.8443,
|
6 |
+
"train_samples": 207864,
|
7 |
+
"train_samples_per_second": 11.286,
|
8 |
+
"train_steps_per_second": 0.088
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1382 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 956,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0010460251046025104,
|
13 |
+
"grad_norm": 4.85831464931585,
|
14 |
+
"learning_rate": 2.0833333333333333e-07,
|
15 |
+
"loss": 1.3092,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.005230125523012552,
|
20 |
+
"grad_norm": 4.698008970388053,
|
21 |
+
"learning_rate": 1.0416666666666667e-06,
|
22 |
+
"loss": 1.2901,
|
23 |
+
"step": 5
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.010460251046025104,
|
27 |
+
"grad_norm": 4.048984012433902,
|
28 |
+
"learning_rate": 2.0833333333333334e-06,
|
29 |
+
"loss": 1.2488,
|
30 |
+
"step": 10
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.015690376569037656,
|
34 |
+
"grad_norm": 1.2617332917985404,
|
35 |
+
"learning_rate": 3.125e-06,
|
36 |
+
"loss": 1.1403,
|
37 |
+
"step": 15
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.02092050209205021,
|
41 |
+
"grad_norm": 0.7560157485938099,
|
42 |
+
"learning_rate": 4.166666666666667e-06,
|
43 |
+
"loss": 1.1238,
|
44 |
+
"step": 20
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.02615062761506276,
|
48 |
+
"grad_norm": 0.6324506842569716,
|
49 |
+
"learning_rate": 5.208333333333334e-06,
|
50 |
+
"loss": 1.0882,
|
51 |
+
"step": 25
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.03138075313807531,
|
55 |
+
"grad_norm": 0.548469635609847,
|
56 |
+
"learning_rate": 6.25e-06,
|
57 |
+
"loss": 1.0972,
|
58 |
+
"step": 30
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.036610878661087864,
|
62 |
+
"grad_norm": 0.5552996818029777,
|
63 |
+
"learning_rate": 7.291666666666667e-06,
|
64 |
+
"loss": 1.0967,
|
65 |
+
"step": 35
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.04184100418410042,
|
69 |
+
"grad_norm": 0.5800275526403403,
|
70 |
+
"learning_rate": 8.333333333333334e-06,
|
71 |
+
"loss": 1.0806,
|
72 |
+
"step": 40
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.04707112970711297,
|
76 |
+
"grad_norm": 0.6526746495693823,
|
77 |
+
"learning_rate": 9.375000000000001e-06,
|
78 |
+
"loss": 1.0799,
|
79 |
+
"step": 45
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.05230125523012552,
|
83 |
+
"grad_norm": 0.5908325566513732,
|
84 |
+
"learning_rate": 1.0416666666666668e-05,
|
85 |
+
"loss": 1.0776,
|
86 |
+
"step": 50
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.05753138075313807,
|
90 |
+
"grad_norm": 0.5391654191606475,
|
91 |
+
"learning_rate": 1.1458333333333333e-05,
|
92 |
+
"loss": 1.0899,
|
93 |
+
"step": 55
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.06276150627615062,
|
97 |
+
"grad_norm": 0.5595510219538938,
|
98 |
+
"learning_rate": 1.25e-05,
|
99 |
+
"loss": 1.0764,
|
100 |
+
"step": 60
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.06799163179916318,
|
104 |
+
"grad_norm": 0.6189231853205227,
|
105 |
+
"learning_rate": 1.3541666666666668e-05,
|
106 |
+
"loss": 1.0822,
|
107 |
+
"step": 65
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.07322175732217573,
|
111 |
+
"grad_norm": 0.6003927282619645,
|
112 |
+
"learning_rate": 1.4583333333333333e-05,
|
113 |
+
"loss": 1.0677,
|
114 |
+
"step": 70
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.07845188284518828,
|
118 |
+
"grad_norm": 0.587656104310443,
|
119 |
+
"learning_rate": 1.5625e-05,
|
120 |
+
"loss": 1.094,
|
121 |
+
"step": 75
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.08368200836820083,
|
125 |
+
"grad_norm": 0.6752900460018412,
|
126 |
+
"learning_rate": 1.6666666666666667e-05,
|
127 |
+
"loss": 1.0929,
|
128 |
+
"step": 80
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.08891213389121339,
|
132 |
+
"grad_norm": 0.584358866439279,
|
133 |
+
"learning_rate": 1.7708333333333335e-05,
|
134 |
+
"loss": 1.1021,
|
135 |
+
"step": 85
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.09414225941422594,
|
139 |
+
"grad_norm": 0.6938741353728844,
|
140 |
+
"learning_rate": 1.8750000000000002e-05,
|
141 |
+
"loss": 1.0856,
|
142 |
+
"step": 90
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.09937238493723849,
|
146 |
+
"grad_norm": 0.5937738979114767,
|
147 |
+
"learning_rate": 1.979166666666667e-05,
|
148 |
+
"loss": 1.0862,
|
149 |
+
"step": 95
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.10460251046025104,
|
153 |
+
"grad_norm": 0.6710102145171454,
|
154 |
+
"learning_rate": 1.9998932457674904e-05,
|
155 |
+
"loss": 1.0933,
|
156 |
+
"step": 100
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.1098326359832636,
|
160 |
+
"grad_norm": 0.5541556578263152,
|
161 |
+
"learning_rate": 1.999459595761682e-05,
|
162 |
+
"loss": 1.1147,
|
163 |
+
"step": 105
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.11506276150627615,
|
167 |
+
"grad_norm": 0.7295308103628182,
|
168 |
+
"learning_rate": 1.9986925223989665e-05,
|
169 |
+
"loss": 1.093,
|
170 |
+
"step": 110
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.1202928870292887,
|
174 |
+
"grad_norm": 0.5550755397232149,
|
175 |
+
"learning_rate": 1.9975922815778082e-05,
|
176 |
+
"loss": 1.0831,
|
177 |
+
"step": 115
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.12552301255230125,
|
181 |
+
"grad_norm": 0.6906078000000908,
|
182 |
+
"learning_rate": 1.996159240342547e-05,
|
183 |
+
"loss": 1.0825,
|
184 |
+
"step": 120
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.1307531380753138,
|
188 |
+
"grad_norm": 0.6064322930924732,
|
189 |
+
"learning_rate": 1.9943938767609515e-05,
|
190 |
+
"loss": 1.0831,
|
191 |
+
"step": 125
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.13598326359832635,
|
195 |
+
"grad_norm": 0.5759088665056421,
|
196 |
+
"learning_rate": 1.9922967797647357e-05,
|
197 |
+
"loss": 1.0905,
|
198 |
+
"step": 130
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.1412133891213389,
|
202 |
+
"grad_norm": 0.5922048567597843,
|
203 |
+
"learning_rate": 1.9898686489530852e-05,
|
204 |
+
"loss": 1.0974,
|
205 |
+
"step": 135
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.14644351464435146,
|
209 |
+
"grad_norm": 0.582760629154959,
|
210 |
+
"learning_rate": 1.9871102943592717e-05,
|
211 |
+
"loss": 1.0731,
|
212 |
+
"step": 140
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.151673640167364,
|
216 |
+
"grad_norm": 0.5685111043758668,
|
217 |
+
"learning_rate": 1.9840226361804223e-05,
|
218 |
+
"loss": 1.1055,
|
219 |
+
"step": 145
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.15690376569037656,
|
223 |
+
"grad_norm": 0.5443024454296611,
|
224 |
+
"learning_rate": 1.9806067044705375e-05,
|
225 |
+
"loss": 1.076,
|
226 |
+
"step": 150
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.16213389121338911,
|
230 |
+
"grad_norm": 0.624292985384766,
|
231 |
+
"learning_rate": 1.9768636387968616e-05,
|
232 |
+
"loss": 1.1064,
|
233 |
+
"step": 155
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.16736401673640167,
|
237 |
+
"grad_norm": 0.6240829821198746,
|
238 |
+
"learning_rate": 1.9727946878597193e-05,
|
239 |
+
"loss": 1.0791,
|
240 |
+
"step": 160
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.17259414225941422,
|
244 |
+
"grad_norm": 0.5276766638385988,
|
245 |
+
"learning_rate": 1.968401209075946e-05,
|
246 |
+
"loss": 1.0839,
|
247 |
+
"step": 165
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.17782426778242677,
|
251 |
+
"grad_norm": 0.5836785578453231,
|
252 |
+
"learning_rate": 1.963684668126046e-05,
|
253 |
+
"loss": 1.1019,
|
254 |
+
"step": 170
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.18305439330543932,
|
258 |
+
"grad_norm": 0.635087703249428,
|
259 |
+
"learning_rate": 1.9586466384652366e-05,
|
260 |
+
"loss": 1.0847,
|
261 |
+
"step": 175
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.18828451882845187,
|
265 |
+
"grad_norm": 0.6401066654821815,
|
266 |
+
"learning_rate": 1.9532888007985408e-05,
|
267 |
+
"loss": 1.0956,
|
268 |
+
"step": 180
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.19351464435146443,
|
272 |
+
"grad_norm": 0.6003213599436353,
|
273 |
+
"learning_rate": 1.9476129425200935e-05,
|
274 |
+
"loss": 1.0937,
|
275 |
+
"step": 185
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.19874476987447698,
|
279 |
+
"grad_norm": 0.6459057767600639,
|
280 |
+
"learning_rate": 1.9416209571168648e-05,
|
281 |
+
"loss": 1.089,
|
282 |
+
"step": 190
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.20397489539748953,
|
286 |
+
"grad_norm": 0.5793932824335415,
|
287 |
+
"learning_rate": 1.9353148435369816e-05,
|
288 |
+
"loss": 1.0906,
|
289 |
+
"step": 195
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.20920502092050208,
|
293 |
+
"grad_norm": 0.5669130898905272,
|
294 |
+
"learning_rate": 1.9286967055228744e-05,
|
295 |
+
"loss": 1.093,
|
296 |
+
"step": 200
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.21443514644351463,
|
300 |
+
"grad_norm": 0.6665999257578469,
|
301 |
+
"learning_rate": 1.9217687509094596e-05,
|
302 |
+
"loss": 1.0759,
|
303 |
+
"step": 205
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.2196652719665272,
|
307 |
+
"grad_norm": 0.6045661696203776,
|
308 |
+
"learning_rate": 1.9145332908875984e-05,
|
309 |
+
"loss": 1.0911,
|
310 |
+
"step": 210
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.22489539748953974,
|
314 |
+
"grad_norm": 0.603921012093451,
|
315 |
+
"learning_rate": 1.9069927392330742e-05,
|
316 |
+
"loss": 1.1017,
|
317 |
+
"step": 215
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.2301255230125523,
|
321 |
+
"grad_norm": 0.6981633005799726,
|
322 |
+
"learning_rate": 1.89914961150135e-05,
|
323 |
+
"loss": 1.082,
|
324 |
+
"step": 220
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.23535564853556484,
|
328 |
+
"grad_norm": 0.5312778797944372,
|
329 |
+
"learning_rate": 1.891006524188368e-05,
|
330 |
+
"loss": 1.0797,
|
331 |
+
"step": 225
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.2405857740585774,
|
335 |
+
"grad_norm": 0.6185885471490489,
|
336 |
+
"learning_rate": 1.8825661938576784e-05,
|
337 |
+
"loss": 1.085,
|
338 |
+
"step": 230
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.24581589958158995,
|
342 |
+
"grad_norm": 0.6020254222541368,
|
343 |
+
"learning_rate": 1.8738314362341828e-05,
|
344 |
+
"loss": 1.0849,
|
345 |
+
"step": 235
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.2510460251046025,
|
349 |
+
"grad_norm": 0.5477699753630808,
|
350 |
+
"learning_rate": 1.864805165264799e-05,
|
351 |
+
"loss": 1.0953,
|
352 |
+
"step": 240
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.25627615062761505,
|
356 |
+
"grad_norm": 0.6850363564163309,
|
357 |
+
"learning_rate": 1.8554903921463578e-05,
|
358 |
+
"loss": 1.0889,
|
359 |
+
"step": 245
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.2615062761506276,
|
363 |
+
"grad_norm": 0.5908540938126509,
|
364 |
+
"learning_rate": 1.8458902243210558e-05,
|
365 |
+
"loss": 1.0822,
|
366 |
+
"step": 250
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.26673640167364016,
|
370 |
+
"grad_norm": 0.6783907257016317,
|
371 |
+
"learning_rate": 1.8360078644398028e-05,
|
372 |
+
"loss": 1.0788,
|
373 |
+
"step": 255
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.2719665271966527,
|
377 |
+
"grad_norm": 0.5917684668235483,
|
378 |
+
"learning_rate": 1.8258466092938042e-05,
|
379 |
+
"loss": 1.101,
|
380 |
+
"step": 260
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.27719665271966526,
|
384 |
+
"grad_norm": 0.5760642704541414,
|
385 |
+
"learning_rate": 1.8154098487147405e-05,
|
386 |
+
"loss": 1.0776,
|
387 |
+
"step": 265
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.2824267782426778,
|
391 |
+
"grad_norm": 0.7830659265090936,
|
392 |
+
"learning_rate": 1.8047010644439074e-05,
|
393 |
+
"loss": 1.0838,
|
394 |
+
"step": 270
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.28765690376569036,
|
398 |
+
"grad_norm": 0.5624324029328165,
|
399 |
+
"learning_rate": 1.7937238289706927e-05,
|
400 |
+
"loss": 1.0821,
|
401 |
+
"step": 275
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.2928870292887029,
|
405 |
+
"grad_norm": 0.6142016239039022,
|
406 |
+
"learning_rate": 1.7824818043407828e-05,
|
407 |
+
"loss": 1.064,
|
408 |
+
"step": 280
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.29811715481171547,
|
412 |
+
"grad_norm": 0.5924790097587224,
|
413 |
+
"learning_rate": 1.7709787409344893e-05,
|
414 |
+
"loss": 1.0749,
|
415 |
+
"step": 285
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.303347280334728,
|
419 |
+
"grad_norm": 0.6228874527190459,
|
420 |
+
"learning_rate": 1.75921847621561e-05,
|
421 |
+
"loss": 1.0863,
|
422 |
+
"step": 290
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.30857740585774057,
|
426 |
+
"grad_norm": 0.6526952399454782,
|
427 |
+
"learning_rate": 1.7472049334512354e-05,
|
428 |
+
"loss": 1.0752,
|
429 |
+
"step": 295
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.3138075313807531,
|
433 |
+
"grad_norm": 0.5460673752687526,
|
434 |
+
"learning_rate": 1.7349421204029343e-05,
|
435 |
+
"loss": 1.0838,
|
436 |
+
"step": 300
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.3190376569037657,
|
440 |
+
"grad_norm": 0.5952113239646497,
|
441 |
+
"learning_rate": 1.7224341279897473e-05,
|
442 |
+
"loss": 1.0937,
|
443 |
+
"step": 305
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.32426778242677823,
|
447 |
+
"grad_norm": 0.6159873510239029,
|
448 |
+
"learning_rate": 1.7096851289234448e-05,
|
449 |
+
"loss": 1.0861,
|
450 |
+
"step": 310
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.3294979079497908,
|
454 |
+
"grad_norm": 0.6664129454325257,
|
455 |
+
"learning_rate": 1.6966993763164928e-05,
|
456 |
+
"loss": 1.0863,
|
457 |
+
"step": 315
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.33472803347280333,
|
461 |
+
"grad_norm": 0.5500624646942581,
|
462 |
+
"learning_rate": 1.6834812022632e-05,
|
463 |
+
"loss": 1.0915,
|
464 |
+
"step": 320
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.3399581589958159,
|
468 |
+
"grad_norm": 0.5592633657451478,
|
469 |
+
"learning_rate": 1.670035016394513e-05,
|
470 |
+
"loss": 1.0875,
|
471 |
+
"step": 325
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.34518828451882844,
|
475 |
+
"grad_norm": 0.5766618518095256,
|
476 |
+
"learning_rate": 1.656365304406953e-05,
|
477 |
+
"loss": 1.0813,
|
478 |
+
"step": 330
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.350418410041841,
|
482 |
+
"grad_norm": 0.5879084875352091,
|
483 |
+
"learning_rate": 1.6424766265661648e-05,
|
484 |
+
"loss": 1.084,
|
485 |
+
"step": 335
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.35564853556485354,
|
489 |
+
"grad_norm": 0.6329467200832875,
|
490 |
+
"learning_rate": 1.6283736161855995e-05,
|
491 |
+
"loss": 1.0772,
|
492 |
+
"step": 340
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 0.3608786610878661,
|
496 |
+
"grad_norm": 0.5327051525622571,
|
497 |
+
"learning_rate": 1.614060978080823e-05,
|
498 |
+
"loss": 1.0927,
|
499 |
+
"step": 345
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.36610878661087864,
|
503 |
+
"grad_norm": 0.5576373339458268,
|
504 |
+
"learning_rate": 1.5995434869999723e-05,
|
505 |
+
"loss": 1.079,
|
506 |
+
"step": 350
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.3713389121338912,
|
510 |
+
"grad_norm": 0.5657380130894529,
|
511 |
+
"learning_rate": 1.584825986030883e-05,
|
512 |
+
"loss": 1.0876,
|
513 |
+
"step": 355
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.37656903765690375,
|
517 |
+
"grad_norm": 0.5680127150496128,
|
518 |
+
"learning_rate": 1.5699133849854164e-05,
|
519 |
+
"loss": 1.0888,
|
520 |
+
"step": 360
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.3817991631799163,
|
524 |
+
"grad_norm": 0.5721025801861312,
|
525 |
+
"learning_rate": 1.5548106587615295e-05,
|
526 |
+
"loss": 1.0669,
|
527 |
+
"step": 365
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.38702928870292885,
|
531 |
+
"grad_norm": 0.5558402829959199,
|
532 |
+
"learning_rate": 1.5395228456836298e-05,
|
533 |
+
"loss": 1.084,
|
534 |
+
"step": 370
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.3922594142259414,
|
538 |
+
"grad_norm": 0.6799222607741628,
|
539 |
+
"learning_rate": 1.524055045821773e-05,
|
540 |
+
"loss": 1.0915,
|
541 |
+
"step": 375
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.39748953974895396,
|
545 |
+
"grad_norm": 0.6425506459433847,
|
546 |
+
"learning_rate": 1.5084124192902612e-05,
|
547 |
+
"loss": 1.0788,
|
548 |
+
"step": 380
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.4027196652719665,
|
552 |
+
"grad_norm": 0.5897131592885358,
|
553 |
+
"learning_rate": 1.4926001845262081e-05,
|
554 |
+
"loss": 1.0831,
|
555 |
+
"step": 385
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.40794979079497906,
|
559 |
+
"grad_norm": 0.5398425974996183,
|
560 |
+
"learning_rate": 1.4766236165486526e-05,
|
561 |
+
"loss": 1.0798,
|
562 |
+
"step": 390
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.4131799163179916,
|
566 |
+
"grad_norm": 0.562078925489584,
|
567 |
+
"learning_rate": 1.4604880451987895e-05,
|
568 |
+
"loss": 1.0763,
|
569 |
+
"step": 395
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.41841004184100417,
|
573 |
+
"grad_norm": 0.5164729530296905,
|
574 |
+
"learning_rate": 1.4441988533619182e-05,
|
575 |
+
"loss": 1.0735,
|
576 |
+
"step": 400
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.4236401673640167,
|
580 |
+
"grad_norm": 0.5832567739541322,
|
581 |
+
"learning_rate": 1.4277614751716911e-05,
|
582 |
+
"loss": 1.0821,
|
583 |
+
"step": 405
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.42887029288702927,
|
587 |
+
"grad_norm": 0.5652212930411926,
|
588 |
+
"learning_rate": 1.4111813941972672e-05,
|
589 |
+
"loss": 1.0961,
|
590 |
+
"step": 410
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.4341004184100418,
|
594 |
+
"grad_norm": 0.6010203451282251,
|
595 |
+
"learning_rate": 1.3944641416139737e-05,
|
596 |
+
"loss": 1.0816,
|
597 |
+
"step": 415
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.4393305439330544,
|
601 |
+
"grad_norm": 0.5630993268496297,
|
602 |
+
"learning_rate": 1.3776152943580846e-05,
|
603 |
+
"loss": 1.0914,
|
604 |
+
"step": 420
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.4445606694560669,
|
608 |
+
"grad_norm": 0.5502230295962955,
|
609 |
+
"learning_rate": 1.3606404732663365e-05,
|
610 |
+
"loss": 1.0697,
|
611 |
+
"step": 425
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.4497907949790795,
|
615 |
+
"grad_norm": 0.6076500784198701,
|
616 |
+
"learning_rate": 1.3435453412007949e-05,
|
617 |
+
"loss": 1.068,
|
618 |
+
"step": 430
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.45502092050209203,
|
622 |
+
"grad_norm": 0.5106137967418161,
|
623 |
+
"learning_rate": 1.3263356011597045e-05,
|
624 |
+
"loss": 1.0758,
|
625 |
+
"step": 435
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.4602510460251046,
|
629 |
+
"grad_norm": 0.5461351720790467,
|
630 |
+
"learning_rate": 1.3090169943749475e-05,
|
631 |
+
"loss": 1.0788,
|
632 |
+
"step": 440
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.46548117154811713,
|
636 |
+
"grad_norm": 0.5139632832447684,
|
637 |
+
"learning_rate": 1.2915952983967477e-05,
|
638 |
+
"loss": 1.0876,
|
639 |
+
"step": 445
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.4707112970711297,
|
643 |
+
"grad_norm": 0.551036425577886,
|
644 |
+
"learning_rate": 1.2740763251662585e-05,
|
645 |
+
"loss": 1.1003,
|
646 |
+
"step": 450
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.47594142259414224,
|
650 |
+
"grad_norm": 0.6151223670580791,
|
651 |
+
"learning_rate": 1.2564659190766788e-05,
|
652 |
+
"loss": 1.0764,
|
653 |
+
"step": 455
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.4811715481171548,
|
657 |
+
"grad_norm": 0.5552173831481524,
|
658 |
+
"learning_rate": 1.2387699550235419e-05,
|
659 |
+
"loss": 1.0858,
|
660 |
+
"step": 460
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.48640167364016734,
|
664 |
+
"grad_norm": 0.4951589610620449,
|
665 |
+
"learning_rate": 1.2209943364448298e-05,
|
666 |
+
"loss": 1.0584,
|
667 |
+
"step": 465
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.4916317991631799,
|
671 |
+
"grad_norm": 0.5475474226252068,
|
672 |
+
"learning_rate": 1.2031449933515625e-05,
|
673 |
+
"loss": 1.0687,
|
674 |
+
"step": 470
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.49686192468619245,
|
678 |
+
"grad_norm": 0.5486935313880071,
|
679 |
+
"learning_rate": 1.1852278803495267e-05,
|
680 |
+
"loss": 1.0573,
|
681 |
+
"step": 475
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.502092050209205,
|
685 |
+
"grad_norm": 0.6521150028759091,
|
686 |
+
"learning_rate": 1.1672489746527979e-05,
|
687 |
+
"loss": 1.0758,
|
688 |
+
"step": 480
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.5073221757322176,
|
692 |
+
"grad_norm": 0.6367797364958308,
|
693 |
+
"learning_rate": 1.1492142740897188e-05,
|
694 |
+
"loss": 1.0677,
|
695 |
+
"step": 485
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.5125523012552301,
|
699 |
+
"grad_norm": 0.5492169886313175,
|
700 |
+
"learning_rate": 1.1311297951020028e-05,
|
701 |
+
"loss": 1.0652,
|
702 |
+
"step": 490
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 0.5177824267782427,
|
706 |
+
"grad_norm": 0.7238966917771047,
|
707 |
+
"learning_rate": 1.1130015707376262e-05,
|
708 |
+
"loss": 1.0715,
|
709 |
+
"step": 495
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 0.5230125523012552,
|
713 |
+
"grad_norm": 0.5393341980142385,
|
714 |
+
"learning_rate": 1.0948356486381829e-05,
|
715 |
+
"loss": 1.0769,
|
716 |
+
"step": 500
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.5282426778242678,
|
720 |
+
"grad_norm": 0.5559622163553696,
|
721 |
+
"learning_rate": 1.0766380890213675e-05,
|
722 |
+
"loss": 1.0806,
|
723 |
+
"step": 505
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.5334728033472803,
|
727 |
+
"grad_norm": 0.5765233869935052,
|
728 |
+
"learning_rate": 1.0584149626592662e-05,
|
729 |
+
"loss": 1.056,
|
730 |
+
"step": 510
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 0.5387029288702929,
|
734 |
+
"grad_norm": 0.6006558028355857,
|
735 |
+
"learning_rate": 1.0401723488531238e-05,
|
736 |
+
"loss": 1.0682,
|
737 |
+
"step": 515
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 0.5439330543933054,
|
741 |
+
"grad_norm": 0.5396974095022056,
|
742 |
+
"learning_rate": 1.0219163334052682e-05,
|
743 |
+
"loss": 1.0817,
|
744 |
+
"step": 520
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.549163179916318,
|
748 |
+
"grad_norm": 0.6140554510099683,
|
749 |
+
"learning_rate": 1.003653006588863e-05,
|
750 |
+
"loss": 1.0757,
|
751 |
+
"step": 525
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.5543933054393305,
|
755 |
+
"grad_norm": 0.5087617662738954,
|
756 |
+
"learning_rate": 9.853884611161709e-06,
|
757 |
+
"loss": 1.047,
|
758 |
+
"step": 530
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 0.5596234309623431,
|
762 |
+
"grad_norm": 0.5112466701463289,
|
763 |
+
"learning_rate": 9.671287901060035e-06,
|
764 |
+
"loss": 1.064,
|
765 |
+
"step": 535
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.5648535564853556,
|
769 |
+
"grad_norm": 0.5633974067279639,
|
770 |
+
"learning_rate": 9.48880085051033e-06,
|
771 |
+
"loss": 1.0734,
|
772 |
+
"step": 540
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 0.5700836820083682,
|
776 |
+
"grad_norm": 0.5557468531733452,
|
777 |
+
"learning_rate": 9.306484337856497e-06,
|
778 |
+
"loss": 1.0777,
|
779 |
+
"step": 545
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 0.5753138075313807,
|
783 |
+
"grad_norm": 0.5271151067730627,
|
784 |
+
"learning_rate": 9.124399184550377e-06,
|
785 |
+
"loss": 1.0817,
|
786 |
+
"step": 550
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 0.5805439330543933,
|
790 |
+
"grad_norm": 0.5448740669834791,
|
791 |
+
"learning_rate": 8.94260613486149e-06,
|
792 |
+
"loss": 1.0757,
|
793 |
+
"step": 555
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 0.5857740585774058,
|
797 |
+
"grad_norm": 0.5155325719909827,
|
798 |
+
"learning_rate": 8.76116583561252e-06,
|
799 |
+
"loss": 1.0589,
|
800 |
+
"step": 560
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 0.5910041841004184,
|
804 |
+
"grad_norm": 0.5378614772721012,
|
805 |
+
"learning_rate": 8.580138815947336e-06,
|
806 |
+
"loss": 1.0651,
|
807 |
+
"step": 565
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.5962343096234309,
|
811 |
+
"grad_norm": 0.6326045695053654,
|
812 |
+
"learning_rate": 8.399585467138215e-06,
|
813 |
+
"loss": 1.0763,
|
814 |
+
"step": 570
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 0.6014644351464435,
|
818 |
+
"grad_norm": 0.6213989271242717,
|
819 |
+
"learning_rate": 8.219566022439128e-06,
|
820 |
+
"loss": 1.0792,
|
821 |
+
"step": 575
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 0.606694560669456,
|
825 |
+
"grad_norm": 0.5547238276934333,
|
826 |
+
"learning_rate": 8.040140536991688e-06,
|
827 |
+
"loss": 1.0767,
|
828 |
+
"step": 580
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 0.6119246861924686,
|
832 |
+
"grad_norm": 0.6071589445644577,
|
833 |
+
"learning_rate": 7.861368867790541e-06,
|
834 |
+
"loss": 1.0792,
|
835 |
+
"step": 585
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 0.6171548117154811,
|
839 |
+
"grad_norm": 0.5293708637565184,
|
840 |
+
"learning_rate": 7.683310653714857e-06,
|
841 |
+
"loss": 1.0723,
|
842 |
+
"step": 590
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 0.6223849372384938,
|
846 |
+
"grad_norm": 0.6845571370634647,
|
847 |
+
"learning_rate": 7.506025295632577e-06,
|
848 |
+
"loss": 1.0646,
|
849 |
+
"step": 595
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.6276150627615062,
|
853 |
+
"grad_norm": 0.5398870120099946,
|
854 |
+
"learning_rate": 7.329571936584072e-06,
|
855 |
+
"loss": 1.0566,
|
856 |
+
"step": 600
|
857 |
+
},
|
858 |
+
{
|
859 |
+
"epoch": 0.6328451882845189,
|
860 |
+
"grad_norm": 0.5549729687939188,
|
861 |
+
"learning_rate": 7.154009442051813e-06,
|
862 |
+
"loss": 1.0562,
|
863 |
+
"step": 605
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 0.6380753138075314,
|
867 |
+
"grad_norm": 0.5739399359103224,
|
868 |
+
"learning_rate": 6.979396380322621e-06,
|
869 |
+
"loss": 1.0744,
|
870 |
+
"step": 610
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 0.643305439330544,
|
874 |
+
"grad_norm": 0.5432529949624418,
|
875 |
+
"learning_rate": 6.805791002949085e-06,
|
876 |
+
"loss": 1.0688,
|
877 |
+
"step": 615
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 0.6485355648535565,
|
881 |
+
"grad_norm": 0.5014458185904755,
|
882 |
+
"learning_rate": 6.63325122531663e-06,
|
883 |
+
"loss": 1.0541,
|
884 |
+
"step": 620
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 0.6537656903765691,
|
888 |
+
"grad_norm": 0.5197776266160257,
|
889 |
+
"learning_rate": 6.461834607322719e-06,
|
890 |
+
"loss": 1.0547,
|
891 |
+
"step": 625
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.6589958158995816,
|
895 |
+
"grad_norm": 0.5327187159562262,
|
896 |
+
"learning_rate": 6.291598334174685e-06,
|
897 |
+
"loss": 1.0572,
|
898 |
+
"step": 630
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 0.6642259414225942,
|
902 |
+
"grad_norm": 0.4979473409535948,
|
903 |
+
"learning_rate": 6.122599197312525e-06,
|
904 |
+
"loss": 1.0858,
|
905 |
+
"step": 635
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 0.6694560669456067,
|
909 |
+
"grad_norm": 0.5036476989509128,
|
910 |
+
"learning_rate": 5.954893575463064e-06,
|
911 |
+
"loss": 1.0637,
|
912 |
+
"step": 640
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 0.6746861924686193,
|
916 |
+
"grad_norm": 0.5228587745934291,
|
917 |
+
"learning_rate": 5.788537415831825e-06,
|
918 |
+
"loss": 1.055,
|
919 |
+
"step": 645
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 0.6799163179916318,
|
923 |
+
"grad_norm": 0.501253029293146,
|
924 |
+
"learning_rate": 5.623586215438813e-06,
|
925 |
+
"loss": 1.0641,
|
926 |
+
"step": 650
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 0.6851464435146444,
|
930 |
+
"grad_norm": 0.5050457318096031,
|
931 |
+
"learning_rate": 5.460095002604533e-06,
|
932 |
+
"loss": 1.0477,
|
933 |
+
"step": 655
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.6903765690376569,
|
937 |
+
"grad_norm": 0.5360440296456983,
|
938 |
+
"learning_rate": 5.298118318592316e-06,
|
939 |
+
"loss": 1.0654,
|
940 |
+
"step": 660
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 0.6956066945606695,
|
944 |
+
"grad_norm": 0.50207454781218,
|
945 |
+
"learning_rate": 5.137710199413182e-06,
|
946 |
+
"loss": 1.0685,
|
947 |
+
"step": 665
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 0.700836820083682,
|
951 |
+
"grad_norm": 0.558550005312336,
|
952 |
+
"learning_rate": 4.978924157799208e-06,
|
953 |
+
"loss": 1.06,
|
954 |
+
"step": 670
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.7060669456066946,
|
958 |
+
"grad_norm": 0.48483916829543067,
|
959 |
+
"learning_rate": 4.821813165351495e-06,
|
960 |
+
"loss": 1.0581,
|
961 |
+
"step": 675
|
962 |
+
},
|
963 |
+
{
|
964 |
+
"epoch": 0.7112970711297071,
|
965 |
+
"grad_norm": 0.49927440612478785,
|
966 |
+
"learning_rate": 4.666429634868651e-06,
|
967 |
+
"loss": 1.0851,
|
968 |
+
"step": 680
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 0.7165271966527197,
|
972 |
+
"grad_norm": 0.48707052941667256,
|
973 |
+
"learning_rate": 4.512825402861686e-06,
|
974 |
+
"loss": 1.0552,
|
975 |
+
"step": 685
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.7217573221757322,
|
979 |
+
"grad_norm": 0.5683679089994613,
|
980 |
+
"learning_rate": 4.361051712261173e-06,
|
981 |
+
"loss": 1.0596,
|
982 |
+
"step": 690
|
983 |
+
},
|
984 |
+
{
|
985 |
+
"epoch": 0.7269874476987448,
|
986 |
+
"grad_norm": 0.5340603274742174,
|
987 |
+
"learning_rate": 4.211159195322404e-06,
|
988 |
+
"loss": 1.0501,
|
989 |
+
"step": 695
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 0.7322175732217573,
|
993 |
+
"grad_norm": 0.5206965463042575,
|
994 |
+
"learning_rate": 4.063197856734295e-06,
|
995 |
+
"loss": 1.0783,
|
996 |
+
"step": 700
|
997 |
+
},
|
998 |
+
{
|
999 |
+
"epoch": 0.7374476987447699,
|
1000 |
+
"grad_norm": 0.5029185927153098,
|
1001 |
+
"learning_rate": 3.917217056937649e-06,
|
1002 |
+
"loss": 1.0636,
|
1003 |
+
"step": 705
|
1004 |
+
},
|
1005 |
+
{
|
1006 |
+
"epoch": 0.7426778242677824,
|
1007 |
+
"grad_norm": 0.5154613274025447,
|
1008 |
+
"learning_rate": 3.773265495658309e-06,
|
1009 |
+
"loss": 1.0655,
|
1010 |
+
"step": 710
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 0.747907949790795,
|
1014 |
+
"grad_norm": 0.4955231762184273,
|
1015 |
+
"learning_rate": 3.6313911956607827e-06,
|
1016 |
+
"loss": 1.0853,
|
1017 |
+
"step": 715
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.7531380753138075,
|
1021 |
+
"grad_norm": 0.513151209360854,
|
1022 |
+
"learning_rate": 3.491641486727645e-06,
|
1023 |
+
"loss": 1.0684,
|
1024 |
+
"step": 720
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"epoch": 0.7583682008368201,
|
1028 |
+
"grad_norm": 0.5327297461286351,
|
1029 |
+
"learning_rate": 3.354062989870166e-06,
|
1030 |
+
"loss": 1.0504,
|
1031 |
+
"step": 725
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 0.7635983263598326,
|
1035 |
+
"grad_norm": 0.5121990852058834,
|
1036 |
+
"learning_rate": 3.2187016017753714e-06,
|
1037 |
+
"loss": 1.066,
|
1038 |
+
"step": 730
|
1039 |
+
},
|
1040 |
+
{
|
1041 |
+
"epoch": 0.7688284518828452,
|
1042 |
+
"grad_norm": 0.5203341394376972,
|
1043 |
+
"learning_rate": 3.085602479494735e-06,
|
1044 |
+
"loss": 1.0602,
|
1045 |
+
"step": 735
|
1046 |
+
},
|
1047 |
+
{
|
1048 |
+
"epoch": 0.7740585774058577,
|
1049 |
+
"grad_norm": 0.5005436050566201,
|
1050 |
+
"learning_rate": 2.954810025379633e-06,
|
1051 |
+
"loss": 1.071,
|
1052 |
+
"step": 740
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 0.7792887029288703,
|
1056 |
+
"grad_norm": 0.502346137505219,
|
1057 |
+
"learning_rate": 2.826367872268543e-06,
|
1058 |
+
"loss": 1.0517,
|
1059 |
+
"step": 745
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.7845188284518828,
|
1063 |
+
"grad_norm": 0.5272314894368499,
|
1064 |
+
"learning_rate": 2.700318868930977e-06,
|
1065 |
+
"loss": 1.0683,
|
1066 |
+
"step": 750
|
1067 |
+
},
|
1068 |
+
{
|
1069 |
+
"epoch": 0.7897489539748954,
|
1070 |
+
"grad_norm": 0.5292107880965233,
|
1071 |
+
"learning_rate": 2.576705065772985e-06,
|
1072 |
+
"loss": 1.0543,
|
1073 |
+
"step": 755
|
1074 |
+
},
|
1075 |
+
{
|
1076 |
+
"epoch": 0.7949790794979079,
|
1077 |
+
"grad_norm": 0.4869311193186611,
|
1078 |
+
"learning_rate": 2.455567700808974e-06,
|
1079 |
+
"loss": 1.0437,
|
1080 |
+
"step": 760
|
1081 |
+
},
|
1082 |
+
{
|
1083 |
+
"epoch": 0.8002092050209205,
|
1084 |
+
"grad_norm": 0.5199956099665775,
|
1085 |
+
"learning_rate": 2.3369471859045558e-06,
|
1086 |
+
"loss": 1.0637,
|
1087 |
+
"step": 765
|
1088 |
+
},
|
1089 |
+
{
|
1090 |
+
"epoch": 0.805439330543933,
|
1091 |
+
"grad_norm": 0.5041918826572614,
|
1092 |
+
"learning_rate": 2.2208830932950175e-06,
|
1093 |
+
"loss": 1.0557,
|
1094 |
+
"step": 770
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 0.8106694560669456,
|
1098 |
+
"grad_norm": 0.4992808348206519,
|
1099 |
+
"learning_rate": 2.107414142383857e-06,
|
1100 |
+
"loss": 1.0636,
|
1101 |
+
"step": 775
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 0.8158995815899581,
|
1105 |
+
"grad_norm": 0.5351058053191133,
|
1106 |
+
"learning_rate": 1.996578186825876e-06,
|
1107 |
+
"loss": 1.0652,
|
1108 |
+
"step": 780
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 0.8211297071129707,
|
1112 |
+
"grad_norm": 0.5071325680716784,
|
1113 |
+
"learning_rate": 1.8884122018990292e-06,
|
1114 |
+
"loss": 1.0575,
|
1115 |
+
"step": 785
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 0.8263598326359832,
|
1119 |
+
"grad_norm": 0.5070573073765244,
|
1120 |
+
"learning_rate": 1.7829522721693738e-06,
|
1121 |
+
"loss": 1.0476,
|
1122 |
+
"step": 790
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 0.8315899581589958,
|
1126 |
+
"grad_norm": 0.5283232962970443,
|
1127 |
+
"learning_rate": 1.680233579453101e-06,
|
1128 |
+
"loss": 1.0604,
|
1129 |
+
"step": 795
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 0.8368200836820083,
|
1133 |
+
"grad_norm": 0.500454736041983,
|
1134 |
+
"learning_rate": 1.5802903910797584e-06,
|
1135 |
+
"loss": 1.0623,
|
1136 |
+
"step": 800
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 0.8420502092050209,
|
1140 |
+
"grad_norm": 0.4991364513451987,
|
1141 |
+
"learning_rate": 1.483156048460561e-06,
|
1142 |
+
"loss": 1.0702,
|
1143 |
+
"step": 805
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 0.8472803347280334,
|
1147 |
+
"grad_norm": 0.5156696669086099,
|
1148 |
+
"learning_rate": 1.3888629559655497e-06,
|
1149 |
+
"loss": 1.065,
|
1150 |
+
"step": 810
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 0.852510460251046,
|
1154 |
+
"grad_norm": 0.495859957636518,
|
1155 |
+
"learning_rate": 1.2974425701133941e-06,
|
1156 |
+
"loss": 1.0519,
|
1157 |
+
"step": 815
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 0.8577405857740585,
|
1161 |
+
"grad_norm": 0.506274711437886,
|
1162 |
+
"learning_rate": 1.2089253890773789e-06,
|
1163 |
+
"loss": 1.0592,
|
1164 |
+
"step": 820
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 0.8629707112970711,
|
1168 |
+
"grad_norm": 0.49088086705348327,
|
1169 |
+
"learning_rate": 1.1233409425110952e-06,
|
1170 |
+
"loss": 1.0562,
|
1171 |
+
"step": 825
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 0.8682008368200836,
|
1175 |
+
"grad_norm": 0.4880905900442435,
|
1176 |
+
"learning_rate": 1.0407177816972558e-06,
|
1177 |
+
"loss": 1.0469,
|
1178 |
+
"step": 830
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 0.8734309623430963,
|
1182 |
+
"grad_norm": 0.5013767019673636,
|
1183 |
+
"learning_rate": 9.610834700228654e-07,
|
1184 |
+
"loss": 1.0776,
|
1185 |
+
"step": 835
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 0.8786610878661087,
|
1189 |
+
"grad_norm": 0.5040841468024664,
|
1190 |
+
"learning_rate": 8.844645737839874e-07,
|
1191 |
+
"loss": 1.0568,
|
1192 |
+
"step": 840
|
1193 |
+
},
|
1194 |
+
{
|
1195 |
+
"epoch": 0.8838912133891214,
|
1196 |
+
"grad_norm": 0.4758757276308106,
|
1197 |
+
"learning_rate": 8.108866533231252e-07,
|
1198 |
+
"loss": 1.0427,
|
1199 |
+
"step": 845
|
1200 |
+
},
|
1201 |
+
{
|
1202 |
+
"epoch": 0.8891213389121339,
|
1203 |
+
"grad_norm": 0.5126814725002861,
|
1204 |
+
"learning_rate": 7.403742545021986e-07,
|
1205 |
+
"loss": 1.0559,
|
1206 |
+
"step": 850
|
1207 |
+
},
|
1208 |
+
{
|
1209 |
+
"epoch": 0.8943514644351465,
|
1210 |
+
"grad_norm": 0.4987765646224313,
|
1211 |
+
"learning_rate": 6.729509005139634e-07,
|
1212 |
+
"loss": 1.0415,
|
1213 |
+
"step": 855
|
1214 |
+
},
|
1215 |
+
{
|
1216 |
+
"epoch": 0.899581589958159,
|
1217 |
+
"grad_norm": 0.5014454129425115,
|
1218 |
+
"learning_rate": 6.086390840345758e-07,
|
1219 |
+
"loss": 1.05,
|
1220 |
+
"step": 860
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 0.9048117154811716,
|
1224 |
+
"grad_norm": 0.48975109580877996,
|
1225 |
+
"learning_rate": 5.474602597199607e-07,
|
1226 |
+
"loss": 1.0704,
|
1227 |
+
"step": 865
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 0.9100418410041841,
|
1231 |
+
"grad_norm": 0.4994701501642807,
|
1232 |
+
"learning_rate": 4.894348370484648e-07,
|
1233 |
+
"loss": 1.0691,
|
1234 |
+
"step": 870
|
1235 |
+
},
|
1236 |
+
{
|
1237 |
+
"epoch": 0.9152719665271967,
|
1238 |
+
"grad_norm": 0.521731055642247,
|
1239 |
+
"learning_rate": 4.34582173512168e-07,
|
1240 |
+
"loss": 1.0677,
|
1241 |
+
"step": 875
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 0.9205020920502092,
|
1245 |
+
"grad_norm": 0.4885441287488048,
|
1246 |
+
"learning_rate": 3.8292056815916965e-07,
|
1247 |
+
"loss": 1.059,
|
1248 |
+
"step": 880
|
1249 |
+
},
|
1250 |
+
{
|
1251 |
+
"epoch": 0.9257322175732218,
|
1252 |
+
"grad_norm": 0.5068844610447545,
|
1253 |
+
"learning_rate": 3.344672554889428e-07,
|
1254 |
+
"loss": 1.0691,
|
1255 |
+
"step": 885
|
1256 |
+
},
|
1257 |
+
{
|
1258 |
+
"epoch": 0.9309623430962343,
|
1259 |
+
"grad_norm": 0.49577008576644055,
|
1260 |
+
"learning_rate": 2.8923839970285473e-07,
|
1261 |
+
"loss": 1.0592,
|
1262 |
+
"step": 890
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 0.9361924686192469,
|
1266 |
+
"grad_norm": 0.4907561902253791,
|
1267 |
+
"learning_rate": 2.472490893117274e-07,
|
1268 |
+
"loss": 1.0458,
|
1269 |
+
"step": 895
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 0.9414225941422594,
|
1273 |
+
"grad_norm": 0.5000871009012277,
|
1274 |
+
"learning_rate": 2.0851333210225032e-07,
|
1275 |
+
"loss": 1.0608,
|
1276 |
+
"step": 900
|
1277 |
+
},
|
1278 |
+
{
|
1279 |
+
"epoch": 0.946652719665272,
|
1280 |
+
"grad_norm": 0.48247289512404495,
|
1281 |
+
"learning_rate": 1.730440504639408e-07,
|
1282 |
+
"loss": 1.058,
|
1283 |
+
"step": 905
|
1284 |
+
},
|
1285 |
+
{
|
1286 |
+
"epoch": 0.9518828451882845,
|
1287 |
+
"grad_norm": 0.48826128008832265,
|
1288 |
+
"learning_rate": 1.408530770781813e-07,
|
1289 |
+
"loss": 1.0526,
|
1290 |
+
"step": 910
|
1291 |
+
},
|
1292 |
+
{
|
1293 |
+
"epoch": 0.9571129707112971,
|
1294 |
+
"grad_norm": 0.4969532853804826,
|
1295 |
+
"learning_rate": 1.1195115097079268e-07,
|
1296 |
+
"loss": 1.0685,
|
1297 |
+
"step": 915
|
1298 |
+
},
|
1299 |
+
{
|
1300 |
+
"epoch": 0.9623430962343096,
|
1301 |
+
"grad_norm": 0.48920579432423383,
|
1302 |
+
"learning_rate": 8.634791392946429e-08,
|
1303 |
+
"loss": 1.0676,
|
1304 |
+
"step": 920
|
1305 |
+
},
|
1306 |
+
{
|
1307 |
+
"epoch": 0.9675732217573222,
|
1308 |
+
"grad_norm": 0.49070804064035406,
|
1309 |
+
"learning_rate": 6.405190728721033e-08,
|
1310 |
+
"loss": 1.0455,
|
1311 |
+
"step": 925
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 0.9728033472803347,
|
1315 |
+
"grad_norm": 0.47721070672447036,
|
1316 |
+
"learning_rate": 4.5070569072952485e-08,
|
1317 |
+
"loss": 1.061,
|
1318 |
+
"step": 930
|
1319 |
+
},
|
1320 |
+
{
|
1321 |
+
"epoch": 0.9780334728033473,
|
1322 |
+
"grad_norm": 0.4960618241854113,
|
1323 |
+
"learning_rate": 2.9410231530168087e-08,
|
1324 |
+
"loss": 1.0499,
|
1325 |
+
"step": 935
|
1326 |
+
},
|
1327 |
+
{
|
1328 |
+
"epoch": 0.9832635983263598,
|
1329 |
+
"grad_norm": 0.4727473862892527,
|
1330 |
+
"learning_rate": 1.7076119004429958e-08,
|
1331 |
+
"loss": 1.0763,
|
1332 |
+
"step": 940
|
1333 |
+
},
|
1334 |
+
{
|
1335 |
+
"epoch": 0.9884937238493724,
|
1336 |
+
"grad_norm": 0.4932911494908516,
|
1337 |
+
"learning_rate": 8.072346200544979e-09,
|
1338 |
+
"loss": 1.0672,
|
1339 |
+
"step": 945
|
1340 |
+
},
|
1341 |
+
{
|
1342 |
+
"epoch": 0.9937238493723849,
|
1343 |
+
"grad_norm": 0.48937555835484964,
|
1344 |
+
"learning_rate": 2.401916809872118e-09,
|
1345 |
+
"loss": 1.0629,
|
1346 |
+
"step": 950
|
1347 |
+
},
|
1348 |
+
{
|
1349 |
+
"epoch": 0.9989539748953975,
|
1350 |
+
"grad_norm": 0.47678060880513334,
|
1351 |
+
"learning_rate": 6.672250828620996e-11,
|
1352 |
+
"loss": 1.0626,
|
1353 |
+
"step": 955
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 1.0,
|
1357 |
+
"eval_loss": 1.0645579099655151,
|
1358 |
+
"eval_runtime": 287.2685,
|
1359 |
+
"eval_samples_per_second": 47.13,
|
1360 |
+
"eval_steps_per_second": 0.738,
|
1361 |
+
"step": 956
|
1362 |
+
},
|
1363 |
+
{
|
1364 |
+
"epoch": 1.0,
|
1365 |
+
"step": 956,
|
1366 |
+
"total_flos": 500925122740224.0,
|
1367 |
+
"train_loss": 1.0766646904426638,
|
1368 |
+
"train_runtime": 10839.8443,
|
1369 |
+
"train_samples_per_second": 11.286,
|
1370 |
+
"train_steps_per_second": 0.088
|
1371 |
+
}
|
1372 |
+
],
|
1373 |
+
"logging_steps": 5,
|
1374 |
+
"max_steps": 956,
|
1375 |
+
"num_input_tokens_seen": 0,
|
1376 |
+
"num_train_epochs": 1,
|
1377 |
+
"save_steps": 100,
|
1378 |
+
"total_flos": 500925122740224.0,
|
1379 |
+
"train_batch_size": 8,
|
1380 |
+
"trial_name": null,
|
1381 |
+
"trial_params": null
|
1382 |
+
}
|