vtiyyal1 commited on
Commit
81151af
1 Parent(s): 559bd7f

Upload folder using huggingface_hub

Browse files
README.md CHANGED
@@ -1,3 +1,202 @@
1
  ---
2
- license: apache-2.0
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ library_name: peft
3
+ base_model: google/gemma-7b-it
4
  ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.9.0
adapter_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "google/gemma-7b-it",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 16,
13
+ "lora_dropout": 0.1,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 64,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "gate_proj",
23
+ "k_proj",
24
+ "q_proj",
25
+ "o_proj",
26
+ "v_proj",
27
+ "down_proj",
28
+ "up_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_dora": false,
32
+ "use_rslora": false
33
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0831cd51005a2e72359d7c111e8bcc3b2b20b1dee89a4d4cc595c475ac8e3f0
3
+ size 400085000
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1d43d8c50d968c26c26e66c6f29bfb2b678efbce00b8a5d3ec2a00b6f76e7d3
3
+ size 401282868
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61b880f2a8181944854bd03a18db9aa8e5866c4a09bade5591298c7b1f1920ae
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48b7fc3797f6245276d62f5f8f8ea70cc0f5e47b5a31bb1299f8a03d566f6127
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,1281 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9,
5
+ "eval_steps": 500,
6
+ "global_step": 4500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "grad_norm": 2.296875,
14
+ "learning_rate": 8.333333333333334e-06,
15
+ "loss": 6.02,
16
+ "step": 25
17
+ },
18
+ {
19
+ "epoch": 0.01,
20
+ "grad_norm": 0.63671875,
21
+ "learning_rate": 1.6666666666666667e-05,
22
+ "loss": 5.3902,
23
+ "step": 50
24
+ },
25
+ {
26
+ "epoch": 0.01,
27
+ "grad_norm": 1.2734375,
28
+ "learning_rate": 2.5e-05,
29
+ "loss": 4.6611,
30
+ "step": 75
31
+ },
32
+ {
33
+ "epoch": 0.02,
34
+ "grad_norm": 7.71875,
35
+ "learning_rate": 3.3333333333333335e-05,
36
+ "loss": 3.8627,
37
+ "step": 100
38
+ },
39
+ {
40
+ "epoch": 0.03,
41
+ "grad_norm": 0.5625,
42
+ "learning_rate": 4.166666666666667e-05,
43
+ "loss": 2.3529,
44
+ "step": 125
45
+ },
46
+ {
47
+ "epoch": 0.03,
48
+ "grad_norm": 0.53515625,
49
+ "learning_rate": 5e-05,
50
+ "loss": 1.4613,
51
+ "step": 150
52
+ },
53
+ {
54
+ "epoch": 0.04,
55
+ "grad_norm": 0.4453125,
56
+ "learning_rate": 4.999672209164081e-05,
57
+ "loss": 1.3771,
58
+ "step": 175
59
+ },
60
+ {
61
+ "epoch": 0.04,
62
+ "grad_norm": 0.5546875,
63
+ "learning_rate": 4.998688922613788e-05,
64
+ "loss": 1.3205,
65
+ "step": 200
66
+ },
67
+ {
68
+ "epoch": 0.04,
69
+ "grad_norm": 0.73046875,
70
+ "learning_rate": 4.997050398198977e-05,
71
+ "loss": 1.2926,
72
+ "step": 225
73
+ },
74
+ {
75
+ "epoch": 0.05,
76
+ "grad_norm": 0.50390625,
77
+ "learning_rate": 4.9947570655942796e-05,
78
+ "loss": 1.2837,
79
+ "step": 250
80
+ },
81
+ {
82
+ "epoch": 0.06,
83
+ "grad_norm": 0.5703125,
84
+ "learning_rate": 4.991809526186424e-05,
85
+ "loss": 1.3392,
86
+ "step": 275
87
+ },
88
+ {
89
+ "epoch": 0.06,
90
+ "grad_norm": 0.46484375,
91
+ "learning_rate": 4.988208552916535e-05,
92
+ "loss": 1.187,
93
+ "step": 300
94
+ },
95
+ {
96
+ "epoch": 0.07,
97
+ "grad_norm": 0.447265625,
98
+ "learning_rate": 4.983955090077444e-05,
99
+ "loss": 1.2047,
100
+ "step": 325
101
+ },
102
+ {
103
+ "epoch": 0.07,
104
+ "grad_norm": 0.494140625,
105
+ "learning_rate": 4.9790502530660635e-05,
106
+ "loss": 1.2062,
107
+ "step": 350
108
+ },
109
+ {
110
+ "epoch": 0.07,
111
+ "grad_norm": 0.55859375,
112
+ "learning_rate": 4.9734953280908904e-05,
113
+ "loss": 1.248,
114
+ "step": 375
115
+ },
116
+ {
117
+ "epoch": 0.08,
118
+ "grad_norm": 0.82421875,
119
+ "learning_rate": 4.967291771834727e-05,
120
+ "loss": 1.225,
121
+ "step": 400
122
+ },
123
+ {
124
+ "epoch": 0.09,
125
+ "grad_norm": 0.484375,
126
+ "learning_rate": 4.960441211072686e-05,
127
+ "loss": 1.2077,
128
+ "step": 425
129
+ },
130
+ {
131
+ "epoch": 0.09,
132
+ "grad_norm": 0.5078125,
133
+ "learning_rate": 4.9529454422455976e-05,
134
+ "loss": 1.2046,
135
+ "step": 450
136
+ },
137
+ {
138
+ "epoch": 0.1,
139
+ "grad_norm": 0.404296875,
140
+ "learning_rate": 4.944806430988927e-05,
141
+ "loss": 1.2055,
142
+ "step": 475
143
+ },
144
+ {
145
+ "epoch": 0.1,
146
+ "grad_norm": 0.546875,
147
+ "learning_rate": 4.936026311617316e-05,
148
+ "loss": 1.2438,
149
+ "step": 500
150
+ },
151
+ {
152
+ "epoch": 0.1,
153
+ "grad_norm": 0.462890625,
154
+ "learning_rate": 4.926607386564898e-05,
155
+ "loss": 1.2093,
156
+ "step": 525
157
+ },
158
+ {
159
+ "epoch": 0.11,
160
+ "grad_norm": 0.50390625,
161
+ "learning_rate": 4.916552125781528e-05,
162
+ "loss": 1.1535,
163
+ "step": 550
164
+ },
165
+ {
166
+ "epoch": 0.12,
167
+ "grad_norm": 0.53125,
168
+ "learning_rate": 4.9058631660850765e-05,
169
+ "loss": 1.2239,
170
+ "step": 575
171
+ },
172
+ {
173
+ "epoch": 0.12,
174
+ "grad_norm": 0.50390625,
175
+ "learning_rate": 4.894543310469968e-05,
176
+ "loss": 1.1454,
177
+ "step": 600
178
+ },
179
+ {
180
+ "epoch": 0.12,
181
+ "grad_norm": 0.61328125,
182
+ "learning_rate": 4.882595527372152e-05,
183
+ "loss": 1.1234,
184
+ "step": 625
185
+ },
186
+ {
187
+ "epoch": 0.13,
188
+ "grad_norm": 0.486328125,
189
+ "learning_rate": 4.870022949890676e-05,
190
+ "loss": 1.1888,
191
+ "step": 650
192
+ },
193
+ {
194
+ "epoch": 0.14,
195
+ "grad_norm": 0.57421875,
196
+ "learning_rate": 4.856828874966086e-05,
197
+ "loss": 1.1476,
198
+ "step": 675
199
+ },
200
+ {
201
+ "epoch": 0.14,
202
+ "grad_norm": 0.435546875,
203
+ "learning_rate": 4.8430167625158595e-05,
204
+ "loss": 1.2208,
205
+ "step": 700
206
+ },
207
+ {
208
+ "epoch": 0.14,
209
+ "grad_norm": 0.49609375,
210
+ "learning_rate": 4.828590234527106e-05,
211
+ "loss": 1.16,
212
+ "step": 725
213
+ },
214
+ {
215
+ "epoch": 0.15,
216
+ "grad_norm": 0.40625,
217
+ "learning_rate": 4.813553074106761e-05,
218
+ "loss": 1.1312,
219
+ "step": 750
220
+ },
221
+ {
222
+ "epoch": 0.15,
223
+ "grad_norm": 0.53125,
224
+ "learning_rate": 4.7979092244895305e-05,
225
+ "loss": 1.1732,
226
+ "step": 775
227
+ },
228
+ {
229
+ "epoch": 0.16,
230
+ "grad_norm": 0.498046875,
231
+ "learning_rate": 4.781662788003851e-05,
232
+ "loss": 1.1404,
233
+ "step": 800
234
+ },
235
+ {
236
+ "epoch": 0.17,
237
+ "grad_norm": 0.484375,
238
+ "learning_rate": 4.764818024996117e-05,
239
+ "loss": 1.1498,
240
+ "step": 825
241
+ },
242
+ {
243
+ "epoch": 0.17,
244
+ "grad_norm": 0.5859375,
245
+ "learning_rate": 4.747379352713489e-05,
246
+ "loss": 1.148,
247
+ "step": 850
248
+ },
249
+ {
250
+ "epoch": 0.17,
251
+ "grad_norm": 0.5234375,
252
+ "learning_rate": 4.7293513441455364e-05,
253
+ "loss": 1.1245,
254
+ "step": 875
255
+ },
256
+ {
257
+ "epoch": 0.18,
258
+ "grad_norm": 0.49609375,
259
+ "learning_rate": 4.710738726825059e-05,
260
+ "loss": 1.0975,
261
+ "step": 900
262
+ },
263
+ {
264
+ "epoch": 0.18,
265
+ "grad_norm": 0.5390625,
266
+ "learning_rate": 4.69154638158837e-05,
267
+ "loss": 1.1204,
268
+ "step": 925
269
+ },
270
+ {
271
+ "epoch": 0.19,
272
+ "grad_norm": 0.55078125,
273
+ "learning_rate": 4.671779341295378e-05,
274
+ "loss": 1.1291,
275
+ "step": 950
276
+ },
277
+ {
278
+ "epoch": 0.2,
279
+ "grad_norm": 0.46484375,
280
+ "learning_rate": 4.6514427895098134e-05,
281
+ "loss": 1.1382,
282
+ "step": 975
283
+ },
284
+ {
285
+ "epoch": 0.2,
286
+ "grad_norm": 0.65625,
287
+ "learning_rate": 4.630542059139924e-05,
288
+ "loss": 1.1861,
289
+ "step": 1000
290
+ },
291
+ {
292
+ "epoch": 0.2,
293
+ "grad_norm": 0.73046875,
294
+ "learning_rate": 4.6090826310400116e-05,
295
+ "loss": 1.1358,
296
+ "step": 1025
297
+ },
298
+ {
299
+ "epoch": 0.21,
300
+ "grad_norm": 0.57421875,
301
+ "learning_rate": 4.587070132573178e-05,
302
+ "loss": 1.115,
303
+ "step": 1050
304
+ },
305
+ {
306
+ "epoch": 0.21,
307
+ "grad_norm": 0.69921875,
308
+ "learning_rate": 4.5645103361356415e-05,
309
+ "loss": 1.0639,
310
+ "step": 1075
311
+ },
312
+ {
313
+ "epoch": 0.22,
314
+ "grad_norm": 0.51953125,
315
+ "learning_rate": 4.541409157643027e-05,
316
+ "loss": 1.1185,
317
+ "step": 1100
318
+ },
319
+ {
320
+ "epoch": 0.23,
321
+ "grad_norm": 0.65234375,
322
+ "learning_rate": 4.517772654979023e-05,
323
+ "loss": 1.1038,
324
+ "step": 1125
325
+ },
326
+ {
327
+ "epoch": 0.23,
328
+ "grad_norm": 0.498046875,
329
+ "learning_rate": 4.493607026406802e-05,
330
+ "loss": 1.0626,
331
+ "step": 1150
332
+ },
333
+ {
334
+ "epoch": 0.23,
335
+ "grad_norm": 0.46484375,
336
+ "learning_rate": 4.4689186089436366e-05,
337
+ "loss": 1.0829,
338
+ "step": 1175
339
+ },
340
+ {
341
+ "epoch": 0.24,
342
+ "grad_norm": 0.53515625,
343
+ "learning_rate": 4.443713876699124e-05,
344
+ "loss": 1.1554,
345
+ "step": 1200
346
+ },
347
+ {
348
+ "epoch": 0.24,
349
+ "grad_norm": 0.486328125,
350
+ "learning_rate": 4.417999439177466e-05,
351
+ "loss": 1.0713,
352
+ "step": 1225
353
+ },
354
+ {
355
+ "epoch": 0.25,
356
+ "grad_norm": 0.5078125,
357
+ "learning_rate": 4.391782039544238e-05,
358
+ "loss": 1.0986,
359
+ "step": 1250
360
+ },
361
+ {
362
+ "epoch": 0.26,
363
+ "grad_norm": 0.474609375,
364
+ "learning_rate": 4.365068552858115e-05,
365
+ "loss": 1.0185,
366
+ "step": 1275
367
+ },
368
+ {
369
+ "epoch": 0.26,
370
+ "grad_norm": 0.53515625,
371
+ "learning_rate": 4.337865984268001e-05,
372
+ "loss": 1.0955,
373
+ "step": 1300
374
+ },
375
+ {
376
+ "epoch": 0.27,
377
+ "grad_norm": 0.58984375,
378
+ "learning_rate": 4.3101814671760546e-05,
379
+ "loss": 1.0747,
380
+ "step": 1325
381
+ },
382
+ {
383
+ "epoch": 0.27,
384
+ "grad_norm": 0.53515625,
385
+ "learning_rate": 4.2820222613670736e-05,
386
+ "loss": 1.0395,
387
+ "step": 1350
388
+ },
389
+ {
390
+ "epoch": 0.28,
391
+ "grad_norm": 0.63671875,
392
+ "learning_rate": 4.253395751104748e-05,
393
+ "loss": 1.0798,
394
+ "step": 1375
395
+ },
396
+ {
397
+ "epoch": 0.28,
398
+ "grad_norm": 0.828125,
399
+ "learning_rate": 4.224309443195261e-05,
400
+ "loss": 1.154,
401
+ "step": 1400
402
+ },
403
+ {
404
+ "epoch": 0.28,
405
+ "grad_norm": 0.6015625,
406
+ "learning_rate": 4.194770965018758e-05,
407
+ "loss": 1.0445,
408
+ "step": 1425
409
+ },
410
+ {
411
+ "epoch": 0.29,
412
+ "grad_norm": 0.5859375,
413
+ "learning_rate": 4.164788062529203e-05,
414
+ "loss": 1.0651,
415
+ "step": 1450
416
+ },
417
+ {
418
+ "epoch": 0.29,
419
+ "grad_norm": 0.5,
420
+ "learning_rate": 4.134368598223132e-05,
421
+ "loss": 1.1505,
422
+ "step": 1475
423
+ },
424
+ {
425
+ "epoch": 0.3,
426
+ "grad_norm": 0.52734375,
427
+ "learning_rate": 4.10352054907785e-05,
428
+ "loss": 1.085,
429
+ "step": 1500
430
+ },
431
+ {
432
+ "epoch": 0.3,
433
+ "grad_norm": 0.53515625,
434
+ "learning_rate": 4.072252004459611e-05,
435
+ "loss": 1.095,
436
+ "step": 1525
437
+ },
438
+ {
439
+ "epoch": 0.31,
440
+ "grad_norm": 0.8046875,
441
+ "learning_rate": 4.0405711640023186e-05,
442
+ "loss": 1.0373,
443
+ "step": 1550
444
+ },
445
+ {
446
+ "epoch": 0.32,
447
+ "grad_norm": 0.6015625,
448
+ "learning_rate": 4.008486335457312e-05,
449
+ "loss": 1.0507,
450
+ "step": 1575
451
+ },
452
+ {
453
+ "epoch": 0.32,
454
+ "grad_norm": 0.578125,
455
+ "learning_rate": 3.976005932514807e-05,
456
+ "loss": 1.0545,
457
+ "step": 1600
458
+ },
459
+ {
460
+ "epoch": 0.33,
461
+ "grad_norm": 0.65625,
462
+ "learning_rate": 3.943138472597549e-05,
463
+ "loss": 1.0342,
464
+ "step": 1625
465
+ },
466
+ {
467
+ "epoch": 0.33,
468
+ "grad_norm": 0.609375,
469
+ "learning_rate": 3.909892574627266e-05,
470
+ "loss": 1.0948,
471
+ "step": 1650
472
+ },
473
+ {
474
+ "epoch": 0.34,
475
+ "grad_norm": 0.59765625,
476
+ "learning_rate": 3.876276956764509e-05,
477
+ "loss": 0.9903,
478
+ "step": 1675
479
+ },
480
+ {
481
+ "epoch": 0.34,
482
+ "grad_norm": 0.5625,
483
+ "learning_rate": 3.84230043412246e-05,
484
+ "loss": 1.058,
485
+ "step": 1700
486
+ },
487
+ {
488
+ "epoch": 0.34,
489
+ "grad_norm": 0.515625,
490
+ "learning_rate": 3.807971916455325e-05,
491
+ "loss": 0.9873,
492
+ "step": 1725
493
+ },
494
+ {
495
+ "epoch": 0.35,
496
+ "grad_norm": 0.55859375,
497
+ "learning_rate": 3.773300405821908e-05,
498
+ "loss": 1.0034,
499
+ "step": 1750
500
+ },
501
+ {
502
+ "epoch": 0.35,
503
+ "grad_norm": 0.60546875,
504
+ "learning_rate": 3.7382949942249694e-05,
505
+ "loss": 1.0152,
506
+ "step": 1775
507
+ },
508
+ {
509
+ "epoch": 0.36,
510
+ "grad_norm": 0.578125,
511
+ "learning_rate": 3.702964861227013e-05,
512
+ "loss": 1.0289,
513
+ "step": 1800
514
+ },
515
+ {
516
+ "epoch": 0.36,
517
+ "grad_norm": 0.65625,
518
+ "learning_rate": 3.6673192715431015e-05,
519
+ "loss": 0.9901,
520
+ "step": 1825
521
+ },
522
+ {
523
+ "epoch": 0.37,
524
+ "grad_norm": 0.63671875,
525
+ "learning_rate": 3.631367572611348e-05,
526
+ "loss": 0.9345,
527
+ "step": 1850
528
+ },
529
+ {
530
+ "epoch": 0.38,
531
+ "grad_norm": 0.671875,
532
+ "learning_rate": 3.595119192141706e-05,
533
+ "loss": 1.035,
534
+ "step": 1875
535
+ },
536
+ {
537
+ "epoch": 0.38,
538
+ "grad_norm": 0.6328125,
539
+ "learning_rate": 3.5585836356437264e-05,
540
+ "loss": 1.0689,
541
+ "step": 1900
542
+ },
543
+ {
544
+ "epoch": 0.39,
545
+ "grad_norm": 0.6015625,
546
+ "learning_rate": 3.521770483933891e-05,
547
+ "loss": 0.9883,
548
+ "step": 1925
549
+ },
550
+ {
551
+ "epoch": 0.39,
552
+ "grad_norm": 0.51953125,
553
+ "learning_rate": 3.484689390623218e-05,
554
+ "loss": 1.0279,
555
+ "step": 1950
556
+ },
557
+ {
558
+ "epoch": 0.4,
559
+ "grad_norm": 0.6484375,
560
+ "learning_rate": 3.447350079585767e-05,
561
+ "loss": 1.0602,
562
+ "step": 1975
563
+ },
564
+ {
565
+ "epoch": 0.4,
566
+ "grad_norm": 0.59375,
567
+ "learning_rate": 3.409762342408719e-05,
568
+ "loss": 1.0178,
569
+ "step": 2000
570
+ },
571
+ {
572
+ "epoch": 0.41,
573
+ "grad_norm": 0.6484375,
574
+ "learning_rate": 3.3719360358247054e-05,
575
+ "loss": 1.0243,
576
+ "step": 2025
577
+ },
578
+ {
579
+ "epoch": 0.41,
580
+ "grad_norm": 0.640625,
581
+ "learning_rate": 3.333881079127052e-05,
582
+ "loss": 1.0175,
583
+ "step": 2050
584
+ },
585
+ {
586
+ "epoch": 0.41,
587
+ "grad_norm": 0.69140625,
588
+ "learning_rate": 3.29560745156861e-05,
589
+ "loss": 0.921,
590
+ "step": 2075
591
+ },
592
+ {
593
+ "epoch": 0.42,
594
+ "grad_norm": 0.65234375,
595
+ "learning_rate": 3.2571251897448765e-05,
596
+ "loss": 0.9597,
597
+ "step": 2100
598
+ },
599
+ {
600
+ "epoch": 0.42,
601
+ "grad_norm": 0.51171875,
602
+ "learning_rate": 3.218444384962071e-05,
603
+ "loss": 0.9761,
604
+ "step": 2125
605
+ },
606
+ {
607
+ "epoch": 0.43,
608
+ "grad_norm": 0.640625,
609
+ "learning_rate": 3.1795751805908573e-05,
610
+ "loss": 0.9706,
611
+ "step": 2150
612
+ },
613
+ {
614
+ "epoch": 0.43,
615
+ "grad_norm": 0.6640625,
616
+ "learning_rate": 3.1405277694064305e-05,
617
+ "loss": 0.932,
618
+ "step": 2175
619
+ },
620
+ {
621
+ "epoch": 0.44,
622
+ "grad_norm": 0.6796875,
623
+ "learning_rate": 3.101312390915634e-05,
624
+ "loss": 0.9486,
625
+ "step": 2200
626
+ },
627
+ {
628
+ "epoch": 0.45,
629
+ "grad_norm": 0.69140625,
630
+ "learning_rate": 3.061939328671824e-05,
631
+ "loss": 1.011,
632
+ "step": 2225
633
+ },
634
+ {
635
+ "epoch": 0.45,
636
+ "grad_norm": 0.60546875,
637
+ "learning_rate": 3.0224189075781884e-05,
638
+ "loss": 0.9463,
639
+ "step": 2250
640
+ },
641
+ {
642
+ "epoch": 0.46,
643
+ "grad_norm": 0.6796875,
644
+ "learning_rate": 2.9827614911802203e-05,
645
+ "loss": 0.9989,
646
+ "step": 2275
647
+ },
648
+ {
649
+ "epoch": 0.46,
650
+ "grad_norm": 0.7109375,
651
+ "learning_rate": 2.9429774789480575e-05,
652
+ "loss": 0.9677,
653
+ "step": 2300
654
+ },
655
+ {
656
+ "epoch": 0.47,
657
+ "grad_norm": 0.62890625,
658
+ "learning_rate": 2.9030773035493997e-05,
659
+ "loss": 0.9739,
660
+ "step": 2325
661
+ },
662
+ {
663
+ "epoch": 0.47,
664
+ "grad_norm": 0.69140625,
665
+ "learning_rate": 2.863071428113726e-05,
666
+ "loss": 1.0254,
667
+ "step": 2350
668
+ },
669
+ {
670
+ "epoch": 0.47,
671
+ "grad_norm": 0.8203125,
672
+ "learning_rate": 2.8229703434885163e-05,
673
+ "loss": 0.9969,
674
+ "step": 2375
675
+ },
676
+ {
677
+ "epoch": 0.48,
678
+ "grad_norm": 0.56640625,
679
+ "learning_rate": 2.782784565488211e-05,
680
+ "loss": 0.9918,
681
+ "step": 2400
682
+ },
683
+ {
684
+ "epoch": 0.48,
685
+ "grad_norm": 0.58203125,
686
+ "learning_rate": 2.7425246321366203e-05,
687
+ "loss": 1.0169,
688
+ "step": 2425
689
+ },
690
+ {
691
+ "epoch": 0.49,
692
+ "grad_norm": 0.75,
693
+ "learning_rate": 2.7022011009035107e-05,
694
+ "loss": 0.9844,
695
+ "step": 2450
696
+ },
697
+ {
698
+ "epoch": 0.49,
699
+ "grad_norm": 0.7265625,
700
+ "learning_rate": 2.6618245459360897e-05,
701
+ "loss": 1.026,
702
+ "step": 2475
703
+ },
704
+ {
705
+ "epoch": 0.5,
706
+ "grad_norm": 0.671875,
707
+ "learning_rate": 2.621405555286121e-05,
708
+ "loss": 0.9333,
709
+ "step": 2500
710
+ },
711
+ {
712
+ "epoch": 0.51,
713
+ "grad_norm": 0.6875,
714
+ "learning_rate": 2.5809547281333902e-05,
715
+ "loss": 1.0336,
716
+ "step": 2525
717
+ },
718
+ {
719
+ "epoch": 0.51,
720
+ "grad_norm": 0.63671875,
721
+ "learning_rate": 2.540482672006254e-05,
722
+ "loss": 0.9375,
723
+ "step": 2550
724
+ },
725
+ {
726
+ "epoch": 0.52,
727
+ "grad_norm": 0.87109375,
728
+ "learning_rate": 2.5e-05,
729
+ "loss": 0.9441,
730
+ "step": 2575
731
+ },
732
+ {
733
+ "epoch": 0.52,
734
+ "grad_norm": 0.7265625,
735
+ "learning_rate": 2.4595173279937464e-05,
736
+ "loss": 0.9643,
737
+ "step": 2600
738
+ },
739
+ {
740
+ "epoch": 0.53,
741
+ "grad_norm": 0.67578125,
742
+ "learning_rate": 2.419045271866611e-05,
743
+ "loss": 0.9172,
744
+ "step": 2625
745
+ },
746
+ {
747
+ "epoch": 0.53,
748
+ "grad_norm": 0.87109375,
749
+ "learning_rate": 2.3785944447138802e-05,
750
+ "loss": 0.8813,
751
+ "step": 2650
752
+ },
753
+ {
754
+ "epoch": 0.54,
755
+ "grad_norm": 0.8046875,
756
+ "learning_rate": 2.338175454063911e-05,
757
+ "loss": 0.9638,
758
+ "step": 2675
759
+ },
760
+ {
761
+ "epoch": 0.54,
762
+ "grad_norm": 0.859375,
763
+ "learning_rate": 2.29779889909649e-05,
764
+ "loss": 0.9476,
765
+ "step": 2700
766
+ },
767
+ {
768
+ "epoch": 0.55,
769
+ "grad_norm": 0.6796875,
770
+ "learning_rate": 2.25747536786338e-05,
771
+ "loss": 0.9536,
772
+ "step": 2725
773
+ },
774
+ {
775
+ "epoch": 0.55,
776
+ "grad_norm": 0.77734375,
777
+ "learning_rate": 2.2172154345117894e-05,
778
+ "loss": 0.9308,
779
+ "step": 2750
780
+ },
781
+ {
782
+ "epoch": 0.56,
783
+ "grad_norm": 0.734375,
784
+ "learning_rate": 2.177029656511485e-05,
785
+ "loss": 0.9432,
786
+ "step": 2775
787
+ },
788
+ {
789
+ "epoch": 0.56,
790
+ "grad_norm": 0.66015625,
791
+ "learning_rate": 2.136928571886275e-05,
792
+ "loss": 0.9253,
793
+ "step": 2800
794
+ },
795
+ {
796
+ "epoch": 0.56,
797
+ "grad_norm": 0.69921875,
798
+ "learning_rate": 2.0969226964506006e-05,
799
+ "loss": 0.9301,
800
+ "step": 2825
801
+ },
802
+ {
803
+ "epoch": 0.57,
804
+ "grad_norm": 0.7578125,
805
+ "learning_rate": 2.0570225210519434e-05,
806
+ "loss": 0.9509,
807
+ "step": 2850
808
+ },
809
+ {
810
+ "epoch": 0.57,
811
+ "grad_norm": 0.7421875,
812
+ "learning_rate": 2.0172385088197803e-05,
813
+ "loss": 0.8995,
814
+ "step": 2875
815
+ },
816
+ {
817
+ "epoch": 0.58,
818
+ "grad_norm": 0.8125,
819
+ "learning_rate": 1.9775810924218125e-05,
820
+ "loss": 0.8682,
821
+ "step": 2900
822
+ },
823
+ {
824
+ "epoch": 0.58,
825
+ "grad_norm": 0.8203125,
826
+ "learning_rate": 1.9380606713281775e-05,
827
+ "loss": 0.9384,
828
+ "step": 2925
829
+ },
830
+ {
831
+ "epoch": 0.59,
832
+ "grad_norm": 0.76171875,
833
+ "learning_rate": 1.8986876090843667e-05,
834
+ "loss": 0.9545,
835
+ "step": 2950
836
+ },
837
+ {
838
+ "epoch": 0.59,
839
+ "grad_norm": 0.74609375,
840
+ "learning_rate": 1.859472230593569e-05,
841
+ "loss": 0.8595,
842
+ "step": 2975
843
+ },
844
+ {
845
+ "epoch": 0.6,
846
+ "grad_norm": 0.8125,
847
+ "learning_rate": 1.820424819409143e-05,
848
+ "loss": 0.9636,
849
+ "step": 3000
850
+ },
851
+ {
852
+ "epoch": 0.6,
853
+ "grad_norm": 0.75390625,
854
+ "learning_rate": 1.7815556150379298e-05,
855
+ "loss": 0.973,
856
+ "step": 3025
857
+ },
858
+ {
859
+ "epoch": 0.61,
860
+ "grad_norm": 0.73828125,
861
+ "learning_rate": 1.7428748102551237e-05,
862
+ "loss": 0.9182,
863
+ "step": 3050
864
+ },
865
+ {
866
+ "epoch": 0.61,
867
+ "grad_norm": 0.85546875,
868
+ "learning_rate": 1.704392548431391e-05,
869
+ "loss": 0.9419,
870
+ "step": 3075
871
+ },
872
+ {
873
+ "epoch": 0.62,
874
+ "grad_norm": 0.71484375,
875
+ "learning_rate": 1.666118920872949e-05,
876
+ "loss": 0.8826,
877
+ "step": 3100
878
+ },
879
+ {
880
+ "epoch": 0.62,
881
+ "grad_norm": 0.83203125,
882
+ "learning_rate": 1.6280639641752942e-05,
883
+ "loss": 0.8989,
884
+ "step": 3125
885
+ },
886
+ {
887
+ "epoch": 0.63,
888
+ "grad_norm": 0.8125,
889
+ "learning_rate": 1.5902376575912815e-05,
890
+ "loss": 0.8946,
891
+ "step": 3150
892
+ },
893
+ {
894
+ "epoch": 0.64,
895
+ "grad_norm": 0.7734375,
896
+ "learning_rate": 1.552649920414233e-05,
897
+ "loss": 0.8636,
898
+ "step": 3175
899
+ },
900
+ {
901
+ "epoch": 0.64,
902
+ "grad_norm": 0.91015625,
903
+ "learning_rate": 1.5153106093767827e-05,
904
+ "loss": 0.9318,
905
+ "step": 3200
906
+ },
907
+ {
908
+ "epoch": 0.65,
909
+ "grad_norm": 0.80078125,
910
+ "learning_rate": 1.4782295160661103e-05,
911
+ "loss": 0.9496,
912
+ "step": 3225
913
+ },
914
+ {
915
+ "epoch": 0.65,
916
+ "grad_norm": 0.734375,
917
+ "learning_rate": 1.4414163643562755e-05,
918
+ "loss": 0.8607,
919
+ "step": 3250
920
+ },
921
+ {
922
+ "epoch": 0.66,
923
+ "grad_norm": 0.7734375,
924
+ "learning_rate": 1.4048808078582942e-05,
925
+ "loss": 0.8367,
926
+ "step": 3275
927
+ },
928
+ {
929
+ "epoch": 0.66,
930
+ "grad_norm": 0.83203125,
931
+ "learning_rate": 1.368632427388653e-05,
932
+ "loss": 0.9584,
933
+ "step": 3300
934
+ },
935
+ {
936
+ "epoch": 0.67,
937
+ "grad_norm": 0.80859375,
938
+ "learning_rate": 1.3326807284568984e-05,
939
+ "loss": 0.8844,
940
+ "step": 3325
941
+ },
942
+ {
943
+ "epoch": 0.67,
944
+ "grad_norm": 0.87890625,
945
+ "learning_rate": 1.2970351387729873e-05,
946
+ "loss": 0.9125,
947
+ "step": 3350
948
+ },
949
+ {
950
+ "epoch": 0.68,
951
+ "grad_norm": 0.74609375,
952
+ "learning_rate": 1.2617050057750322e-05,
953
+ "loss": 0.9229,
954
+ "step": 3375
955
+ },
956
+ {
957
+ "epoch": 0.68,
958
+ "grad_norm": 0.80078125,
959
+ "learning_rate": 1.2266995941780934e-05,
960
+ "loss": 0.9541,
961
+ "step": 3400
962
+ },
963
+ {
964
+ "epoch": 0.69,
965
+ "grad_norm": 0.8359375,
966
+ "learning_rate": 1.1920280835446748e-05,
967
+ "loss": 0.8816,
968
+ "step": 3425
969
+ },
970
+ {
971
+ "epoch": 0.69,
972
+ "grad_norm": 0.82421875,
973
+ "learning_rate": 1.1576995658775405e-05,
974
+ "loss": 0.862,
975
+ "step": 3450
976
+ },
977
+ {
978
+ "epoch": 0.69,
979
+ "grad_norm": 0.80078125,
980
+ "learning_rate": 1.1237230432354912e-05,
981
+ "loss": 0.8541,
982
+ "step": 3475
983
+ },
984
+ {
985
+ "epoch": 0.7,
986
+ "grad_norm": 0.8203125,
987
+ "learning_rate": 1.0901074253727336e-05,
988
+ "loss": 0.8586,
989
+ "step": 3500
990
+ },
991
+ {
992
+ "epoch": 0.7,
993
+ "grad_norm": 0.7890625,
994
+ "learning_rate": 1.0568615274024522e-05,
995
+ "loss": 0.9033,
996
+ "step": 3525
997
+ },
998
+ {
999
+ "epoch": 0.71,
1000
+ "grad_norm": 0.7890625,
1001
+ "learning_rate": 1.0239940674851941e-05,
1002
+ "loss": 0.8456,
1003
+ "step": 3550
1004
+ },
1005
+ {
1006
+ "epoch": 0.71,
1007
+ "grad_norm": 0.91796875,
1008
+ "learning_rate": 9.915136645426884e-06,
1009
+ "loss": 0.9165,
1010
+ "step": 3575
1011
+ },
1012
+ {
1013
+ "epoch": 0.72,
1014
+ "grad_norm": 0.80859375,
1015
+ "learning_rate": 9.594288359976817e-06,
1016
+ "loss": 0.8225,
1017
+ "step": 3600
1018
+ },
1019
+ {
1020
+ "epoch": 0.72,
1021
+ "grad_norm": 0.85546875,
1022
+ "learning_rate": 9.277479955403887e-06,
1023
+ "loss": 0.815,
1024
+ "step": 3625
1025
+ },
1026
+ {
1027
+ "epoch": 0.73,
1028
+ "grad_norm": 0.6640625,
1029
+ "learning_rate": 8.964794509221508e-06,
1030
+ "loss": 0.8517,
1031
+ "step": 3650
1032
+ },
1033
+ {
1034
+ "epoch": 0.73,
1035
+ "grad_norm": 0.8125,
1036
+ "learning_rate": 8.656314017768693e-06,
1037
+ "loss": 0.9108,
1038
+ "step": 3675
1039
+ },
1040
+ {
1041
+ "epoch": 0.74,
1042
+ "grad_norm": 0.8671875,
1043
+ "learning_rate": 8.352119374707978e-06,
1044
+ "loss": 0.8665,
1045
+ "step": 3700
1046
+ },
1047
+ {
1048
+ "epoch": 0.74,
1049
+ "grad_norm": 0.8359375,
1050
+ "learning_rate": 8.052290349812419e-06,
1051
+ "loss": 0.875,
1052
+ "step": 3725
1053
+ },
1054
+ {
1055
+ "epoch": 0.75,
1056
+ "grad_norm": 0.8359375,
1057
+ "learning_rate": 7.756905568047393e-06,
1058
+ "loss": 0.9181,
1059
+ "step": 3750
1060
+ },
1061
+ {
1062
+ "epoch": 0.76,
1063
+ "grad_norm": 0.91015625,
1064
+ "learning_rate": 7.466042488952521e-06,
1065
+ "loss": 0.8715,
1066
+ "step": 3775
1067
+ },
1068
+ {
1069
+ "epoch": 0.76,
1070
+ "grad_norm": 0.74609375,
1071
+ "learning_rate": 7.179777386329276e-06,
1072
+ "loss": 0.9051,
1073
+ "step": 3800
1074
+ },
1075
+ {
1076
+ "epoch": 0.77,
1077
+ "grad_norm": 0.796875,
1078
+ "learning_rate": 6.898185328239468e-06,
1079
+ "loss": 0.871,
1080
+ "step": 3825
1081
+ },
1082
+ {
1083
+ "epoch": 0.77,
1084
+ "grad_norm": 0.71875,
1085
+ "learning_rate": 6.621340157319997e-06,
1086
+ "loss": 0.8633,
1087
+ "step": 3850
1088
+ },
1089
+ {
1090
+ "epoch": 0.78,
1091
+ "grad_norm": 0.98046875,
1092
+ "learning_rate": 6.349314471418849e-06,
1093
+ "loss": 0.8513,
1094
+ "step": 3875
1095
+ },
1096
+ {
1097
+ "epoch": 0.78,
1098
+ "grad_norm": 0.81640625,
1099
+ "learning_rate": 6.082179604557617e-06,
1100
+ "loss": 0.8063,
1101
+ "step": 3900
1102
+ },
1103
+ {
1104
+ "epoch": 0.79,
1105
+ "grad_norm": 0.80078125,
1106
+ "learning_rate": 5.820005608225346e-06,
1107
+ "loss": 0.8652,
1108
+ "step": 3925
1109
+ },
1110
+ {
1111
+ "epoch": 0.79,
1112
+ "grad_norm": 0.81640625,
1113
+ "learning_rate": 5.562861233008774e-06,
1114
+ "loss": 0.872,
1115
+ "step": 3950
1116
+ },
1117
+ {
1118
+ "epoch": 0.8,
1119
+ "grad_norm": 0.74609375,
1120
+ "learning_rate": 5.310813910563644e-06,
1121
+ "loss": 0.849,
1122
+ "step": 3975
1123
+ },
1124
+ {
1125
+ "epoch": 0.8,
1126
+ "grad_norm": 0.79296875,
1127
+ "learning_rate": 5.063929735931985e-06,
1128
+ "loss": 0.8926,
1129
+ "step": 4000
1130
+ },
1131
+ {
1132
+ "epoch": 0.81,
1133
+ "grad_norm": 0.77734375,
1134
+ "learning_rate": 4.8222734502097665e-06,
1135
+ "loss": 0.8093,
1136
+ "step": 4025
1137
+ },
1138
+ {
1139
+ "epoch": 0.81,
1140
+ "grad_norm": 0.8515625,
1141
+ "learning_rate": 4.585908423569724e-06,
1142
+ "loss": 0.8563,
1143
+ "step": 4050
1144
+ },
1145
+ {
1146
+ "epoch": 0.81,
1147
+ "grad_norm": 0.97265625,
1148
+ "learning_rate": 4.35489663864359e-06,
1149
+ "loss": 0.8393,
1150
+ "step": 4075
1151
+ },
1152
+ {
1153
+ "epoch": 0.82,
1154
+ "grad_norm": 0.8984375,
1155
+ "learning_rate": 4.129298674268225e-06,
1156
+ "loss": 0.9031,
1157
+ "step": 4100
1158
+ },
1159
+ {
1160
+ "epoch": 0.82,
1161
+ "grad_norm": 0.9296875,
1162
+ "learning_rate": 3.90917368959989e-06,
1163
+ "loss": 0.8981,
1164
+ "step": 4125
1165
+ },
1166
+ {
1167
+ "epoch": 0.83,
1168
+ "grad_norm": 0.8828125,
1169
+ "learning_rate": 3.694579408600771e-06,
1170
+ "loss": 0.8628,
1171
+ "step": 4150
1172
+ },
1173
+ {
1174
+ "epoch": 0.83,
1175
+ "grad_norm": 0.796875,
1176
+ "learning_rate": 3.4855721049018688e-06,
1177
+ "loss": 0.8707,
1178
+ "step": 4175
1179
+ },
1180
+ {
1181
+ "epoch": 0.84,
1182
+ "grad_norm": 0.88671875,
1183
+ "learning_rate": 3.2822065870462217e-06,
1184
+ "loss": 0.8423,
1185
+ "step": 4200
1186
+ },
1187
+ {
1188
+ "epoch": 0.84,
1189
+ "grad_norm": 0.7578125,
1190
+ "learning_rate": 3.08453618411631e-06,
1191
+ "loss": 0.8448,
1192
+ "step": 4225
1193
+ },
1194
+ {
1195
+ "epoch": 0.85,
1196
+ "grad_norm": 0.8984375,
1197
+ "learning_rate": 2.892612731749414e-06,
1198
+ "loss": 0.8743,
1199
+ "step": 4250
1200
+ },
1201
+ {
1202
+ "epoch": 0.85,
1203
+ "grad_norm": 0.8125,
1204
+ "learning_rate": 2.7064865585446434e-06,
1205
+ "loss": 0.8389,
1206
+ "step": 4275
1207
+ },
1208
+ {
1209
+ "epoch": 0.86,
1210
+ "grad_norm": 0.8046875,
1211
+ "learning_rate": 2.52620647286512e-06,
1212
+ "loss": 0.8437,
1213
+ "step": 4300
1214
+ },
1215
+ {
1216
+ "epoch": 0.86,
1217
+ "grad_norm": 0.92578125,
1218
+ "learning_rate": 2.351819750038828e-06,
1219
+ "loss": 0.7811,
1220
+ "step": 4325
1221
+ },
1222
+ {
1223
+ "epoch": 0.87,
1224
+ "grad_norm": 0.8359375,
1225
+ "learning_rate": 2.183372119961499e-06,
1226
+ "loss": 0.8266,
1227
+ "step": 4350
1228
+ },
1229
+ {
1230
+ "epoch": 0.88,
1231
+ "grad_norm": 0.9296875,
1232
+ "learning_rate": 2.020907755104698e-06,
1233
+ "loss": 0.8374,
1234
+ "step": 4375
1235
+ },
1236
+ {
1237
+ "epoch": 0.88,
1238
+ "grad_norm": 0.80859375,
1239
+ "learning_rate": 1.864469258932397e-06,
1240
+ "loss": 0.9058,
1241
+ "step": 4400
1242
+ },
1243
+ {
1244
+ "epoch": 0.89,
1245
+ "grad_norm": 0.78125,
1246
+ "learning_rate": 1.7140976547289438e-06,
1247
+ "loss": 0.8627,
1248
+ "step": 4425
1249
+ },
1250
+ {
1251
+ "epoch": 0.89,
1252
+ "grad_norm": 0.8359375,
1253
+ "learning_rate": 1.5698323748414124e-06,
1254
+ "loss": 0.8706,
1255
+ "step": 4450
1256
+ },
1257
+ {
1258
+ "epoch": 0.9,
1259
+ "grad_norm": 0.95703125,
1260
+ "learning_rate": 1.4317112503391432e-06,
1261
+ "loss": 0.8315,
1262
+ "step": 4475
1263
+ },
1264
+ {
1265
+ "epoch": 0.9,
1266
+ "grad_norm": 0.80859375,
1267
+ "learning_rate": 1.2997705010932393e-06,
1268
+ "loss": 0.791,
1269
+ "step": 4500
1270
+ }
1271
+ ],
1272
+ "logging_steps": 25,
1273
+ "max_steps": 5000,
1274
+ "num_input_tokens_seen": 0,
1275
+ "num_train_epochs": 9223372036854775807,
1276
+ "save_steps": 500,
1277
+ "total_flos": 8.79346273222656e+17,
1278
+ "train_batch_size": 1,
1279
+ "trial_name": null,
1280
+ "trial_params": null
1281
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3460479bf9efa1f6bc1b563fc6a790fb29cfb70a59fda8cbb0bab8e475316c7e
3
+ size 4856