Model save

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,63 @@
+---
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: zephyr-2b-gemma-dft
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://zebra.wandb.io/cto/distillm/runs/kje9xugl)
+# zephyr-2b-gemma-dft
+
+This model was trained from scratch on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0000
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.0           | 0.9982 | 270  | 0.0000          |
+
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9981515711645101,
+    "total_flos": 5.260333472022528e+16,
+    "train_loss": 1.8035727003330572e-05,
+    "train_runtime": 2689.0507,
+    "train_samples": 6750,
+    "train_samples_per_second": 3.217,
+    "train_steps_per_second": 0.1
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "data/gemma-2b",
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.4",
+  "use_cache": false,
+  "vocab_size": 256000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.42.4"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:166c2cc2ac8f29542b11f7812cc6cdded64345b787b9b74e50c194790584c068
+size 4945242264

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:403d33ecb881a9ae12700a261993eb4f1ad36a361fbb628ffaa31bf3ff3456e1
+size 67121608

model.safetensors.index.json

@@ -0,0 +1,171 @@
+{
+  "metadata": {
+    "total_size": 5012344832
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

runs/Jul16_18-12-23_ale-distillm-4-0-0/events.out.tfevents.1721149966.ale-distillm-4-0-0.7658.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3fd7babffa0e9fdf4182b38c8071b38d38e57db672c81819305ab7b2c25308b
+size 5055

runs/Jul16_18-20-11_ale-distillm-4-0-0/events.out.tfevents.1721150424.ale-distillm-4-0-0.7949.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dea8980e272d221ff59bdececffe023d523e0f5c7ea68a8138516094410725c
+size 5055

runs/Jul16_18-22-23_ale-distillm-4-0-0/events.out.tfevents.1721150560.ale-distillm-4-0-0.8244.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ec26a1e5af465720c232ff6afd65bcf34cb3b4236f6949ac2c779afd12ca9e1
+size 5055

runs/Jul17_11-03-52_ale-distillm-4-0-0/events.out.tfevents.1721210651.ale-distillm-4-0-0.8479.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab42917c254853050095e429ea9fa59b50da47494cc10f674f45746b5af02157
+size 5055

runs/Jul17_11-04-55_ale-distillm-4-0-0/events.out.tfevents.1721210714.ale-distillm-4-0-0.8662.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd05f663af210ef2de49565416459d12abe15960a1d0ca0ef8e93f9a27e60667
+size 5055

runs/Jul17_11-27-53_ale-distillm-4-0-0/events.out.tfevents.1721212093.ale-distillm-4-0-0.9186.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7092880334181484ee43a723e7d22e66b6de34a8cbe72a7dcf9d52af122ab904
+size 5055

runs/Jul17_11-28-42_ale-distillm-4-0-0/events.out.tfevents.1721212137.ale-distillm-4-0-0.9386.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10974222cd7e984ba0a009524eb7a3965f59d8f6208cbedeabbac4ee4fa19ea8
+size 5055

runs/Jul17_11-36-32_ale-distillm-4-0-0/events.out.tfevents.1721212618.ale-distillm-4-0-0.10015.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62fdc7be20c86a69d309ce6af7a7c50639a02b8e7de9d509ac308c0b23e82404
+size 5087

runs/Jul17_12-10-33_ale-distillm-4-0-0/events.out.tfevents.1721214649.ale-distillm-4-0-0.10368.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d504a55c4df859f7b471970c71509272d6e3c76a47e81f8c2827d94fe569a30
+size 5087

runs/Jul17_12-21-11_ale-distillm-4-0-0/events.out.tfevents.1721215291.ale-distillm-4-0-0.10647.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de0fd73ff50ab253c90f3faea2b74cca9edbd46576b1426bce9795a85bf1f192
+size 5087

runs/Jul17_12-24-53_ale-distillm-4-0-0/events.out.tfevents.1721215508.ale-distillm-4-0-0.10860.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d89929bcc3fd481899f8559e297cf7bb0cdfc326d73f26b2f7e3effe48cab54a
+size 5087

runs/Jul17_12-34-51_ale-distillm-4-0-0/events.out.tfevents.1721216106.ale-distillm-4-0-0.11082.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e331c25188f28d5bc3abbb566730a28f1f2e55951a6977142f82c12a8d02eba
+size 5087

runs/Jul17_12-49-34_ale-distillm-4-0-0/events.out.tfevents.1721216989.ale-distillm-4-0-0.11354.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e6ca33ae652b061367a63f8f1b6fc552bade2c1b46865945c26ab75da85d45c
+size 5087

runs/Jul17_13-09-32_ale-distillm-4-0-0/events.out.tfevents.1721218187.ale-distillm-4-0-0.11829.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d5066ae9eb68702efa52f40e4f1da54ac877df37ee04c6e08a1b3221e51f4b0
+size 5087

runs/Jul17_13-12-55_ale-distillm-4-0-0/events.out.tfevents.1721218390.ale-distillm-4-0-0.12123.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfec3c1845089a56f9c4052ac42d774681dd9de81d94f1c3a011a19b4411385b
+size 5087

runs/Jul17_13-13-43_ale-distillm-4-0-0/events.out.tfevents.1721218443.ale-distillm-4-0-0.12398.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a02770839a18eafe9c4ccd86088dfe776131f259dc5cefe54cafdf6e2af6a80
+size 5087

runs/Jul17_13-15-39_ale-distillm-4-0-0/events.out.tfevents.1721218553.ale-distillm-4-0-0.12607.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82b3eab5c1ae70676d9c87154ba38f758706702098852d920488668a4b087883
+size 5087

runs/Jul17_14-00-44_ale-distillm-4-0-0/events.out.tfevents.1721221259.ale-distillm-4-0-0.12881.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e75cf2449c6b5e5f670f83bedafe082f8af03fabe57bb4a87069cf184d66e24
+size 5086

runs/Jul17_14-03-37_ale-distillm-4-0-0/events.out.tfevents.1721221432.ale-distillm-4-0-0.13176.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b62346c4be5f816886cd8150e9b5cea91e925ef1fe0b69e429afac7f246bd9d8
+size 5293

runs/Jul17_14-04-49_ale-distillm-4-0-0/events.out.tfevents.1721221504.ale-distillm-4-0-0.13609.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d0752a22e6ccc4555c0088bba4b252394e7d820fa8705a44de664a8976d91b0
+size 10683

runs/Jul17_14-34-01_ale-distillm-8-0-0/events.out.tfevents.1721223728.ale-distillm-8-0-0.2624.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7df9453a58a3ca60873c86a217f0bae83aa115c813e28a46964b8ba7e71c2017
+size 5086

runs/Jul17_15-05-14_ale-distillm-8-0-0/events.out.tfevents.1721225135.ale-distillm-8-0-0.3160.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f4878ae53ad6ee4ba5b16b14ec9d342a6fbbad39fd2128a4f0ba2ecbde8fe61
+size 5086

runs/Jul17_15-07-31_ale-distillm-8-0-0/events.out.tfevents.1721225298.ale-distillm-8-0-0.3493.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a00ba0003f0a4cde97006a9e21f770f96592121961afb70d388006836c199d7
+size 5055

runs/Jul17_15-09-08_ale-distillm-8-0-0/events.out.tfevents.1721225375.ale-distillm-8-0-0.3899.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bdd1f0813c8b60d1f4b34ce47b8ea4e5c7d1b43860e78c077825e7ea9cf4317
+size 5086

runs/Jul17_15-12-13_ale-distillm-8-0-0/events.out.tfevents.1721225558.ale-distillm-8-0-0.4304.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a0ca0aaee6a6430d4f9b1066718e40063917f12e389ef25a4abafdbeb985755
+size 5086

runs/Jul17_15-33-25_ale-distillm-8-0-0/events.out.tfevents.1721226819.ale-distillm-8-0-0.5027.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8070ed496d5878317b955ed8a5d1816159305f6bbe985116856e738db1bc7213
+size 5087

runs/Jul17_15-37-19_ale-distillm-8-0-0/events.out.tfevents.1721227053.ale-distillm-8-0-0.5333.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f33fb6cda0b4825a7ea029b5d0605168b9d5953d56bbdc777e0328e70df2b15
+size 5087

runs/Jul17_15-40-39_ale-distillm-8-0-0/events.out.tfevents.1721227253.ale-distillm-8-0-0.5662.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cac9787042f38c64ac3b2e1613e873a2742f4a51ff3d01ce6f6d46c3d3d9fb75
+size 5086

runs/Jul18_08-21-26_ale-distillm-8-0-0/events.out.tfevents.1721287323.ale-distillm-8-0-0.6210.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6cc02a9efbe2cf2bfcf8b86f7413ed2343329ef3b2e8ef5a0a5ad12a5229fd7
+size 5086

runs/Jul18_08-31-58_ale-distillm-8-0-0/events.out.tfevents.1721287933.ale-distillm-8-0-0.6609.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f94b89bc6517903a538b4226559f1c7b3514d65825523c35b092168e38fc933
+size 5086

runs/Jul18_08-40-57_ale-distillm-8-0-0/events.out.tfevents.1721288501.ale-distillm-8-0-0.6938.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:181ebcd6a237e3dc441423c263d92f59515b9fe360230c3975ea5b4884bf3968
+size 5087

runs/Jul18_08-43-48_ale-distillm-8-0-0/events.out.tfevents.1721288655.ale-distillm-8-0-0.7340.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92b329679593a913b57ebbd352b51290c373d722856a81414310179ddb390e31
+size 5087

runs/Jul18_08-46-16_ale-distillm-8-0-0/events.out.tfevents.1721288790.ale-distillm-8-0-0.7769.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:613b4ea765180d4441669aec54fc86fdaf2ec2c47e4d93c4087d06a81851c06a
+size 5087

runs/Jul18_09-00-59_ale-distillm-8-0-0/events.out.tfevents.1721289676.ale-distillm-8-0-0.8302.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54270265a73720dc8cfccae09b7f417ddf47f864ed882690595f45c97f7c99e7
+size 5087

runs/Jul18_09-05-16_ale-distillm-8-0-0/events.out.tfevents.1721289930.ale-distillm-8-0-0.8653.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f27c23d77905906192737e0a47e380d3e8696e8cac96a8195e191aa8985a3be
+size 5087

runs/Jul18_09-10-17_ale-distillm-8-0-0/events.out.tfevents.1721290244.ale-distillm-8-0-0.8992.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6d4da68d9d2699e78cb8e1ed236a71d9a17fe9961352b90c0c297887b31cda8
+size 5087

runs/Jul18_09-31-51_ale-distillm-8-0-0/events.out.tfevents.1721291539.ale-distillm-8-0-0.9393.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bbb367b444b118e93749b3754682a00b7a4f939f4cae26dfe31092003da1458
+size 5087

runs/Jul18_10-30-23_ale-distillm-8-0-0/events.out.tfevents.1721295036.ale-distillm-8-0-0.9995.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64ab4b2fafc194e75ea4b22c184da37e276a5dfc0f455985cf5b11bd30fc3e42
+size 5087

runs/Jul18_10-32-15_ale-distillm-8-0-0/events.out.tfevents.1721295149.ale-distillm-8-0-0.10329.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e07330b91d46f77e9e070fbc84a9935b72c420fe737aa7230e5520a95874354
+size 5087

runs/Jul18_10-33-27_ale-distillm-8-0-0/events.out.tfevents.1721295221.ale-distillm-8-0-0.10663.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f817bea72f99381b3353b349c888a22643e26c8da63fab5aea868192bfd4a84b
+size 5086

runs/Jul18_10-50-46_ale-distillm-8-0-0/events.out.tfevents.1721296272.ale-distillm-8-0-0.11268.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c32a5d43ca36b20dba38d667c2bc977e48f4f07b7435862ddfba35334bd24574
+size 5087

runs/Jul18_10-51-50_ale-distillm-8-0-0/events.out.tfevents.1721296327.ale-distillm-8-0-0.11641.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b213f9e2452b5046a74bdf9a7f70307de998700b372bc1dc810065f5b2592b30
+size 5087