satvik-dixit commited on
Commit
fd0d8ab
1 Parent(s): 635daba

Uploaded checkpoint-2000

Browse files
README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: meta-llama/Meta-Llama-3-8B
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 0.8.2
adapter_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B",
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": 256,
13
+ "lora_dropout": 0.05,
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
+ "up_proj",
23
+ "gate_proj",
24
+ "q_proj",
25
+ "k_proj",
26
+ "v_proj",
27
+ "o_proj",
28
+ "down_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_rslora": false
32
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79b1554758768e2f7f1b29a11707aafc99dd95582ffe0ec0f9643f9faae605c2
3
+ size 671149168
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5e808f30cf216fcbc6562b580d65fee4339e955964abef534d4dce75ee2291d
3
+ size 1342555602
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60a158d213701f7c694bac391507fad82c19d6af52c9f5283fb8d59da595ed18
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2af80d0aa5baa7857ca944ff75c2949797b73df774b45412b073c1bde7f3745
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,1437 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.1,
5
+ "eval_steps": 1000,
6
+ "global_step": 2000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "grad_norm": 31.81644058227539,
14
+ "learning_rate": 8e-08,
15
+ "loss": 1.5083,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.0,
20
+ "grad_norm": 16.249370574951172,
21
+ "learning_rate": 1.7000000000000001e-07,
22
+ "loss": 1.2724,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.0,
27
+ "grad_norm": 16.85301971435547,
28
+ "learning_rate": 2.7e-07,
29
+ "loss": 1.2571,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.0,
34
+ "grad_norm": 12.382726669311523,
35
+ "learning_rate": 3.7e-07,
36
+ "loss": 1.101,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.0,
41
+ "grad_norm": 43.00498962402344,
42
+ "learning_rate": 4.6999999999999995e-07,
43
+ "loss": 1.2847,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.0,
48
+ "grad_norm": 16.686534881591797,
49
+ "learning_rate": 5.6e-07,
50
+ "loss": 0.8594,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.0,
55
+ "grad_norm": 23.844993591308594,
56
+ "learning_rate": 6.6e-07,
57
+ "loss": 0.7645,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.0,
62
+ "grad_norm": 15.943971633911133,
63
+ "learning_rate": 7.599999999999999e-07,
64
+ "loss": 0.7681,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.0,
69
+ "grad_norm": 12.707146644592285,
70
+ "learning_rate": 8.599999999999999e-07,
71
+ "loss": 0.8728,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.01,
76
+ "grad_norm": 13.066338539123535,
77
+ "learning_rate": 9.6e-07,
78
+ "loss": 0.7508,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.01,
83
+ "grad_norm": 21.36861801147461,
84
+ "learning_rate": 9.993939393939394e-07,
85
+ "loss": 0.999,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.01,
90
+ "grad_norm": 23.451967239379883,
91
+ "learning_rate": 9.983838383838383e-07,
92
+ "loss": 0.8396,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.01,
97
+ "grad_norm": 14.662145614624023,
98
+ "learning_rate": 9.973737373737373e-07,
99
+ "loss": 1.0884,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.01,
104
+ "grad_norm": 9.530464172363281,
105
+ "learning_rate": 9.963636363636362e-07,
106
+ "loss": 0.8505,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.01,
111
+ "grad_norm": 30.15620231628418,
112
+ "learning_rate": 9.953535353535352e-07,
113
+ "loss": 0.971,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.01,
118
+ "grad_norm": 43.50494384765625,
119
+ "learning_rate": 9.943434343434343e-07,
120
+ "loss": 0.9758,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.01,
125
+ "grad_norm": 18.704565048217773,
126
+ "learning_rate": 9.933333333333333e-07,
127
+ "loss": 1.1095,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.01,
132
+ "grad_norm": 51.077552795410156,
133
+ "learning_rate": 9.923232323232322e-07,
134
+ "loss": 1.0251,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.01,
139
+ "grad_norm": 32.405906677246094,
140
+ "learning_rate": 9.913131313131314e-07,
141
+ "loss": 0.8793,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.01,
146
+ "grad_norm": 35.2808952331543,
147
+ "learning_rate": 9.903030303030303e-07,
148
+ "loss": 0.6785,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.01,
153
+ "grad_norm": 17.738399505615234,
154
+ "learning_rate": 9.892929292929293e-07,
155
+ "loss": 0.8258,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.01,
160
+ "grad_norm": 8.202994346618652,
161
+ "learning_rate": 9.882828282828282e-07,
162
+ "loss": 0.8756,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.01,
167
+ "grad_norm": 16.26487159729004,
168
+ "learning_rate": 9.872727272727272e-07,
169
+ "loss": 1.0467,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.01,
174
+ "grad_norm": 32.37431335449219,
175
+ "learning_rate": 9.862626262626263e-07,
176
+ "loss": 0.9119,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.01,
181
+ "grad_norm": 5.586151599884033,
182
+ "learning_rate": 9.852525252525253e-07,
183
+ "loss": 0.8556,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.01,
188
+ "grad_norm": 16.249475479125977,
189
+ "learning_rate": 9.842424242424242e-07,
190
+ "loss": 0.7945,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.01,
195
+ "grad_norm": 60.965965270996094,
196
+ "learning_rate": 9.832323232323231e-07,
197
+ "loss": 1.0668,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.01,
202
+ "grad_norm": 19.940616607666016,
203
+ "learning_rate": 9.82222222222222e-07,
204
+ "loss": 0.6501,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.01,
209
+ "grad_norm": 26.526460647583008,
210
+ "learning_rate": 9.812121212121212e-07,
211
+ "loss": 1.0423,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.01,
216
+ "grad_norm": 27.455795288085938,
217
+ "learning_rate": 9.802020202020202e-07,
218
+ "loss": 0.6693,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.02,
223
+ "grad_norm": 18.113489151000977,
224
+ "learning_rate": 9.791919191919191e-07,
225
+ "loss": 0.4784,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.02,
230
+ "grad_norm": 29.75452423095703,
231
+ "learning_rate": 9.78181818181818e-07,
232
+ "loss": 0.5004,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.02,
237
+ "grad_norm": 24.82709503173828,
238
+ "learning_rate": 9.77171717171717e-07,
239
+ "loss": 0.8543,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.02,
244
+ "grad_norm": 22.23027801513672,
245
+ "learning_rate": 9.761616161616162e-07,
246
+ "loss": 0.796,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.02,
251
+ "grad_norm": 9.593890190124512,
252
+ "learning_rate": 9.751515151515151e-07,
253
+ "loss": 0.672,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.02,
258
+ "grad_norm": 19.550216674804688,
259
+ "learning_rate": 9.74141414141414e-07,
260
+ "loss": 0.5915,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.02,
265
+ "grad_norm": 18.101367950439453,
266
+ "learning_rate": 9.731313131313132e-07,
267
+ "loss": 0.8967,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.02,
272
+ "grad_norm": 6.973883152008057,
273
+ "learning_rate": 9.721212121212122e-07,
274
+ "loss": 0.7841,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.02,
279
+ "grad_norm": 18.076982498168945,
280
+ "learning_rate": 9.711111111111111e-07,
281
+ "loss": 0.7783,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.02,
286
+ "grad_norm": 1.5223013162612915,
287
+ "learning_rate": 9.7010101010101e-07,
288
+ "loss": 0.8647,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.02,
293
+ "grad_norm": 14.444634437561035,
294
+ "learning_rate": 9.69090909090909e-07,
295
+ "loss": 0.6745,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.02,
300
+ "grad_norm": 41.90908432006836,
301
+ "learning_rate": 9.680808080808082e-07,
302
+ "loss": 1.0749,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.02,
307
+ "grad_norm": 27.912317276000977,
308
+ "learning_rate": 9.67070707070707e-07,
309
+ "loss": 0.5588,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.02,
314
+ "grad_norm": 22.31749725341797,
315
+ "learning_rate": 9.66060606060606e-07,
316
+ "loss": 0.7683,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.02,
321
+ "grad_norm": 57.88829040527344,
322
+ "learning_rate": 9.65050505050505e-07,
323
+ "loss": 0.5442,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.02,
328
+ "grad_norm": 43.25718688964844,
329
+ "learning_rate": 9.64040404040404e-07,
330
+ "loss": 0.8028,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.02,
335
+ "grad_norm": 21.001134872436523,
336
+ "learning_rate": 9.630303030303029e-07,
337
+ "loss": 0.7472,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.02,
342
+ "grad_norm": 13.919650077819824,
343
+ "learning_rate": 9.62020202020202e-07,
344
+ "loss": 0.5318,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.02,
349
+ "grad_norm": 26.845335006713867,
350
+ "learning_rate": 9.61010101010101e-07,
351
+ "loss": 1.012,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.03,
356
+ "grad_norm": 20.0955867767334,
357
+ "learning_rate": 9.6e-07,
358
+ "loss": 0.9174,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.03,
363
+ "grad_norm": 9.6511812210083,
364
+ "learning_rate": 9.589898989898989e-07,
365
+ "loss": 0.691,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.03,
370
+ "grad_norm": 12.875068664550781,
371
+ "learning_rate": 9.579797979797978e-07,
372
+ "loss": 0.7781,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.03,
377
+ "grad_norm": 28.99612045288086,
378
+ "learning_rate": 9.56969696969697e-07,
379
+ "loss": 0.7791,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.03,
384
+ "grad_norm": 47.6656379699707,
385
+ "learning_rate": 9.55959595959596e-07,
386
+ "loss": 0.6166,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.03,
391
+ "grad_norm": 59.9251708984375,
392
+ "learning_rate": 9.549494949494948e-07,
393
+ "loss": 0.6836,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.03,
398
+ "grad_norm": 34.26139831542969,
399
+ "learning_rate": 9.53939393939394e-07,
400
+ "loss": 0.4317,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.03,
405
+ "grad_norm": 47.75581359863281,
406
+ "learning_rate": 9.529292929292929e-07,
407
+ "loss": 0.5685,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.03,
412
+ "grad_norm": 63.76834487915039,
413
+ "learning_rate": 9.519191919191919e-07,
414
+ "loss": 0.8805,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.03,
419
+ "grad_norm": 22.971323013305664,
420
+ "learning_rate": 9.509090909090908e-07,
421
+ "loss": 0.8103,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 0.03,
426
+ "grad_norm": 42.151161193847656,
427
+ "learning_rate": 9.498989898989899e-07,
428
+ "loss": 0.7563,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 0.03,
433
+ "grad_norm": 13.12915325164795,
434
+ "learning_rate": 9.488888888888888e-07,
435
+ "loss": 0.6844,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 0.03,
440
+ "grad_norm": 37.901973724365234,
441
+ "learning_rate": 9.478787878787879e-07,
442
+ "loss": 0.7467,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 0.03,
447
+ "grad_norm": 29.114883422851562,
448
+ "learning_rate": 9.468686868686868e-07,
449
+ "loss": 0.7759,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 0.03,
454
+ "grad_norm": 37.42153549194336,
455
+ "learning_rate": 9.458585858585858e-07,
456
+ "loss": 0.7221,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 0.03,
461
+ "grad_norm": 46.287559509277344,
462
+ "learning_rate": 9.448484848484848e-07,
463
+ "loss": 0.7219,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 0.03,
468
+ "grad_norm": 76.34626770019531,
469
+ "learning_rate": 9.438383838383838e-07,
470
+ "loss": 0.6938,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 0.03,
475
+ "grad_norm": 20.480300903320312,
476
+ "learning_rate": 9.428282828282827e-07,
477
+ "loss": 0.8135,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 0.03,
482
+ "grad_norm": 9.508841514587402,
483
+ "learning_rate": 9.418181818181818e-07,
484
+ "loss": 0.6024,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 0.03,
489
+ "grad_norm": 29.385066986083984,
490
+ "learning_rate": 9.408080808080807e-07,
491
+ "loss": 0.8891,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 0.04,
496
+ "grad_norm": 13.06400203704834,
497
+ "learning_rate": 9.397979797979797e-07,
498
+ "loss": 0.6723,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 0.04,
503
+ "grad_norm": 36.94926071166992,
504
+ "learning_rate": 9.387878787878788e-07,
505
+ "loss": 0.5682,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 0.04,
510
+ "grad_norm": 30.849035263061523,
511
+ "learning_rate": 9.377777777777777e-07,
512
+ "loss": 0.6693,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 0.04,
517
+ "grad_norm": 27.781005859375,
518
+ "learning_rate": 9.367676767676768e-07,
519
+ "loss": 0.7705,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 0.04,
524
+ "grad_norm": 5.268486976623535,
525
+ "learning_rate": 9.357575757575757e-07,
526
+ "loss": 0.7672,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 0.04,
531
+ "grad_norm": 70.79887390136719,
532
+ "learning_rate": 9.347474747474747e-07,
533
+ "loss": 0.7617,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 0.04,
538
+ "grad_norm": 71.6796875,
539
+ "learning_rate": 9.337373737373737e-07,
540
+ "loss": 0.5425,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 0.04,
545
+ "grad_norm": 21.205890655517578,
546
+ "learning_rate": 9.327272727272727e-07,
547
+ "loss": 0.6768,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 0.04,
552
+ "grad_norm": 38.276634216308594,
553
+ "learning_rate": 9.317171717171717e-07,
554
+ "loss": 0.8681,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 0.04,
559
+ "grad_norm": 17.904993057250977,
560
+ "learning_rate": 9.307070707070707e-07,
561
+ "loss": 0.7128,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 0.04,
566
+ "grad_norm": 32.66667938232422,
567
+ "learning_rate": 9.296969696969696e-07,
568
+ "loss": 0.8662,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 0.04,
573
+ "grad_norm": 7.020589828491211,
574
+ "learning_rate": 9.286868686868687e-07,
575
+ "loss": 0.7344,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 0.04,
580
+ "grad_norm": 33.822608947753906,
581
+ "learning_rate": 9.276767676767676e-07,
582
+ "loss": 0.7825,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 0.04,
587
+ "grad_norm": 21.147552490234375,
588
+ "learning_rate": 9.266666666666665e-07,
589
+ "loss": 0.7716,
590
+ "step": 830
591
+ },
592
+ {
593
+ "epoch": 0.04,
594
+ "grad_norm": 22.41349983215332,
595
+ "learning_rate": 9.256565656565656e-07,
596
+ "loss": 0.4673,
597
+ "step": 840
598
+ },
599
+ {
600
+ "epoch": 0.04,
601
+ "grad_norm": 24.813737869262695,
602
+ "learning_rate": 9.246464646464645e-07,
603
+ "loss": 0.7137,
604
+ "step": 850
605
+ },
606
+ {
607
+ "epoch": 0.04,
608
+ "grad_norm": 31.02164649963379,
609
+ "learning_rate": 9.236363636363636e-07,
610
+ "loss": 1.0195,
611
+ "step": 860
612
+ },
613
+ {
614
+ "epoch": 0.04,
615
+ "grad_norm": 19.22023582458496,
616
+ "learning_rate": 9.226262626262625e-07,
617
+ "loss": 0.8201,
618
+ "step": 870
619
+ },
620
+ {
621
+ "epoch": 0.04,
622
+ "grad_norm": 21.087970733642578,
623
+ "learning_rate": 9.216161616161616e-07,
624
+ "loss": 0.6296,
625
+ "step": 880
626
+ },
627
+ {
628
+ "epoch": 0.04,
629
+ "grad_norm": 8.970023155212402,
630
+ "learning_rate": 9.206060606060606e-07,
631
+ "loss": 0.3712,
632
+ "step": 890
633
+ },
634
+ {
635
+ "epoch": 0.04,
636
+ "grad_norm": 28.498889923095703,
637
+ "learning_rate": 9.195959595959596e-07,
638
+ "loss": 0.7953,
639
+ "step": 900
640
+ },
641
+ {
642
+ "epoch": 0.05,
643
+ "grad_norm": 21.259479522705078,
644
+ "learning_rate": 9.185858585858585e-07,
645
+ "loss": 0.7346,
646
+ "step": 910
647
+ },
648
+ {
649
+ "epoch": 0.05,
650
+ "grad_norm": 13.871064186096191,
651
+ "learning_rate": 9.175757575757576e-07,
652
+ "loss": 0.6644,
653
+ "step": 920
654
+ },
655
+ {
656
+ "epoch": 0.05,
657
+ "grad_norm": 44.91512680053711,
658
+ "learning_rate": 9.165656565656565e-07,
659
+ "loss": 0.5467,
660
+ "step": 930
661
+ },
662
+ {
663
+ "epoch": 0.05,
664
+ "grad_norm": 11.775423049926758,
665
+ "learning_rate": 9.155555555555556e-07,
666
+ "loss": 0.5149,
667
+ "step": 940
668
+ },
669
+ {
670
+ "epoch": 0.05,
671
+ "grad_norm": 35.62663650512695,
672
+ "learning_rate": 9.145454545454545e-07,
673
+ "loss": 0.6002,
674
+ "step": 950
675
+ },
676
+ {
677
+ "epoch": 0.05,
678
+ "grad_norm": 32.12046813964844,
679
+ "learning_rate": 9.135353535353535e-07,
680
+ "loss": 0.8875,
681
+ "step": 960
682
+ },
683
+ {
684
+ "epoch": 0.05,
685
+ "grad_norm": 37.11963653564453,
686
+ "learning_rate": 9.126262626262626e-07,
687
+ "loss": 0.9515,
688
+ "step": 970
689
+ },
690
+ {
691
+ "epoch": 0.05,
692
+ "grad_norm": 21.641096115112305,
693
+ "learning_rate": 9.116161616161616e-07,
694
+ "loss": 0.7849,
695
+ "step": 980
696
+ },
697
+ {
698
+ "epoch": 0.05,
699
+ "grad_norm": 29.253921508789062,
700
+ "learning_rate": 9.106060606060606e-07,
701
+ "loss": 0.5926,
702
+ "step": 990
703
+ },
704
+ {
705
+ "epoch": 0.05,
706
+ "grad_norm": 27.01972198486328,
707
+ "learning_rate": 9.095959595959596e-07,
708
+ "loss": 0.7061,
709
+ "step": 1000
710
+ },
711
+ {
712
+ "epoch": 0.05,
713
+ "eval_loss": 0.725902259349823,
714
+ "eval_runtime": 274.8847,
715
+ "eval_samples_per_second": 3.638,
716
+ "eval_steps_per_second": 3.638,
717
+ "step": 1000
718
+ },
719
+ {
720
+ "epoch": 0.05,
721
+ "grad_norm": 16.84354019165039,
722
+ "learning_rate": 9.085858585858586e-07,
723
+ "loss": 0.6186,
724
+ "step": 1010
725
+ },
726
+ {
727
+ "epoch": 0.05,
728
+ "grad_norm": 36.384700775146484,
729
+ "learning_rate": 9.075757575757576e-07,
730
+ "loss": 0.8362,
731
+ "step": 1020
732
+ },
733
+ {
734
+ "epoch": 0.05,
735
+ "grad_norm": 37.640892028808594,
736
+ "learning_rate": 9.065656565656565e-07,
737
+ "loss": 0.7901,
738
+ "step": 1030
739
+ },
740
+ {
741
+ "epoch": 0.05,
742
+ "grad_norm": 44.735076904296875,
743
+ "learning_rate": 9.055555555555556e-07,
744
+ "loss": 0.5116,
745
+ "step": 1040
746
+ },
747
+ {
748
+ "epoch": 0.05,
749
+ "grad_norm": 46.5770263671875,
750
+ "learning_rate": 9.045454545454545e-07,
751
+ "loss": 0.7274,
752
+ "step": 1050
753
+ },
754
+ {
755
+ "epoch": 0.05,
756
+ "grad_norm": 0.10406364500522614,
757
+ "learning_rate": 9.035353535353534e-07,
758
+ "loss": 0.4903,
759
+ "step": 1060
760
+ },
761
+ {
762
+ "epoch": 0.05,
763
+ "grad_norm": 18.263145446777344,
764
+ "learning_rate": 9.025252525252525e-07,
765
+ "loss": 0.7371,
766
+ "step": 1070
767
+ },
768
+ {
769
+ "epoch": 0.05,
770
+ "grad_norm": 33.42209243774414,
771
+ "learning_rate": 9.015151515151514e-07,
772
+ "loss": 0.8111,
773
+ "step": 1080
774
+ },
775
+ {
776
+ "epoch": 0.05,
777
+ "grad_norm": 48.237525939941406,
778
+ "learning_rate": 9.005050505050504e-07,
779
+ "loss": 0.6233,
780
+ "step": 1090
781
+ },
782
+ {
783
+ "epoch": 0.06,
784
+ "grad_norm": 1.5421327352523804,
785
+ "learning_rate": 8.994949494949494e-07,
786
+ "loss": 0.6609,
787
+ "step": 1100
788
+ },
789
+ {
790
+ "epoch": 0.06,
791
+ "grad_norm": 29.761442184448242,
792
+ "learning_rate": 8.984848484848484e-07,
793
+ "loss": 0.4407,
794
+ "step": 1110
795
+ },
796
+ {
797
+ "epoch": 0.06,
798
+ "grad_norm": 31.435007095336914,
799
+ "learning_rate": 8.974747474747474e-07,
800
+ "loss": 0.7207,
801
+ "step": 1120
802
+ },
803
+ {
804
+ "epoch": 0.06,
805
+ "grad_norm": 28.20315170288086,
806
+ "learning_rate": 8.964646464646465e-07,
807
+ "loss": 0.6879,
808
+ "step": 1130
809
+ },
810
+ {
811
+ "epoch": 0.06,
812
+ "grad_norm": 19.431041717529297,
813
+ "learning_rate": 8.954545454545454e-07,
814
+ "loss": 0.7292,
815
+ "step": 1140
816
+ },
817
+ {
818
+ "epoch": 0.06,
819
+ "grad_norm": 40.8221435546875,
820
+ "learning_rate": 8.944444444444445e-07,
821
+ "loss": 0.9112,
822
+ "step": 1150
823
+ },
824
+ {
825
+ "epoch": 0.06,
826
+ "grad_norm": 4.42428731918335,
827
+ "learning_rate": 8.934343434343434e-07,
828
+ "loss": 0.484,
829
+ "step": 1160
830
+ },
831
+ {
832
+ "epoch": 0.06,
833
+ "grad_norm": 24.146841049194336,
834
+ "learning_rate": 8.924242424242425e-07,
835
+ "loss": 0.4881,
836
+ "step": 1170
837
+ },
838
+ {
839
+ "epoch": 0.06,
840
+ "grad_norm": 52.02534866333008,
841
+ "learning_rate": 8.914141414141414e-07,
842
+ "loss": 0.8042,
843
+ "step": 1180
844
+ },
845
+ {
846
+ "epoch": 0.06,
847
+ "grad_norm": 26.81230926513672,
848
+ "learning_rate": 8.904040404040404e-07,
849
+ "loss": 0.6995,
850
+ "step": 1190
851
+ },
852
+ {
853
+ "epoch": 0.06,
854
+ "grad_norm": 9.775701522827148,
855
+ "learning_rate": 8.893939393939394e-07,
856
+ "loss": 0.8203,
857
+ "step": 1200
858
+ },
859
+ {
860
+ "epoch": 0.06,
861
+ "grad_norm": 20.65981674194336,
862
+ "learning_rate": 8.883838383838383e-07,
863
+ "loss": 0.9154,
864
+ "step": 1210
865
+ },
866
+ {
867
+ "epoch": 0.06,
868
+ "grad_norm": 20.086986541748047,
869
+ "learning_rate": 8.873737373737373e-07,
870
+ "loss": 0.4731,
871
+ "step": 1220
872
+ },
873
+ {
874
+ "epoch": 0.06,
875
+ "grad_norm": 20.6555233001709,
876
+ "learning_rate": 8.863636363636363e-07,
877
+ "loss": 0.7798,
878
+ "step": 1230
879
+ },
880
+ {
881
+ "epoch": 0.06,
882
+ "grad_norm": 13.60240364074707,
883
+ "learning_rate": 8.853535353535353e-07,
884
+ "loss": 0.6382,
885
+ "step": 1240
886
+ },
887
+ {
888
+ "epoch": 0.06,
889
+ "grad_norm": 20.39061737060547,
890
+ "learning_rate": 8.843434343434343e-07,
891
+ "loss": 0.6077,
892
+ "step": 1250
893
+ },
894
+ {
895
+ "epoch": 0.06,
896
+ "grad_norm": 14.251206398010254,
897
+ "learning_rate": 8.833333333333333e-07,
898
+ "loss": 0.5736,
899
+ "step": 1260
900
+ },
901
+ {
902
+ "epoch": 0.06,
903
+ "grad_norm": 63.768611907958984,
904
+ "learning_rate": 8.823232323232322e-07,
905
+ "loss": 0.7059,
906
+ "step": 1270
907
+ },
908
+ {
909
+ "epoch": 0.06,
910
+ "grad_norm": 44.81045150756836,
911
+ "learning_rate": 8.813131313131313e-07,
912
+ "loss": 0.6352,
913
+ "step": 1280
914
+ },
915
+ {
916
+ "epoch": 0.06,
917
+ "grad_norm": 15.952017784118652,
918
+ "learning_rate": 8.803030303030302e-07,
919
+ "loss": 0.7523,
920
+ "step": 1290
921
+ },
922
+ {
923
+ "epoch": 0.07,
924
+ "grad_norm": 27.234148025512695,
925
+ "learning_rate": 8.792929292929293e-07,
926
+ "loss": 0.4924,
927
+ "step": 1300
928
+ },
929
+ {
930
+ "epoch": 0.07,
931
+ "grad_norm": 44.29439163208008,
932
+ "learning_rate": 8.782828282828283e-07,
933
+ "loss": 0.6422,
934
+ "step": 1310
935
+ },
936
+ {
937
+ "epoch": 0.07,
938
+ "grad_norm": 35.106658935546875,
939
+ "learning_rate": 8.772727272727273e-07,
940
+ "loss": 0.655,
941
+ "step": 1320
942
+ },
943
+ {
944
+ "epoch": 0.07,
945
+ "grad_norm": 2.1618399620056152,
946
+ "learning_rate": 8.762626262626263e-07,
947
+ "loss": 0.6463,
948
+ "step": 1330
949
+ },
950
+ {
951
+ "epoch": 0.07,
952
+ "grad_norm": 36.30659866333008,
953
+ "learning_rate": 8.752525252525253e-07,
954
+ "loss": 0.5618,
955
+ "step": 1340
956
+ },
957
+ {
958
+ "epoch": 0.07,
959
+ "grad_norm": 18.705991744995117,
960
+ "learning_rate": 8.742424242424242e-07,
961
+ "loss": 0.5887,
962
+ "step": 1350
963
+ },
964
+ {
965
+ "epoch": 0.07,
966
+ "grad_norm": 2.828080654144287,
967
+ "learning_rate": 8.732323232323232e-07,
968
+ "loss": 0.6611,
969
+ "step": 1360
970
+ },
971
+ {
972
+ "epoch": 0.07,
973
+ "grad_norm": 47.979820251464844,
974
+ "learning_rate": 8.722222222222222e-07,
975
+ "loss": 0.4975,
976
+ "step": 1370
977
+ },
978
+ {
979
+ "epoch": 0.07,
980
+ "grad_norm": 25.263946533203125,
981
+ "learning_rate": 8.712121212121211e-07,
982
+ "loss": 0.761,
983
+ "step": 1380
984
+ },
985
+ {
986
+ "epoch": 0.07,
987
+ "grad_norm": 0.21978527307510376,
988
+ "learning_rate": 8.702020202020202e-07,
989
+ "loss": 0.5013,
990
+ "step": 1390
991
+ },
992
+ {
993
+ "epoch": 0.07,
994
+ "grad_norm": 15.600090026855469,
995
+ "learning_rate": 8.691919191919191e-07,
996
+ "loss": 0.5375,
997
+ "step": 1400
998
+ },
999
+ {
1000
+ "epoch": 0.07,
1001
+ "grad_norm": 25.815698623657227,
1002
+ "learning_rate": 8.681818181818182e-07,
1003
+ "loss": 0.8176,
1004
+ "step": 1410
1005
+ },
1006
+ {
1007
+ "epoch": 0.07,
1008
+ "grad_norm": 44.83120346069336,
1009
+ "learning_rate": 8.671717171717171e-07,
1010
+ "loss": 0.5207,
1011
+ "step": 1420
1012
+ },
1013
+ {
1014
+ "epoch": 0.07,
1015
+ "grad_norm": 20.984037399291992,
1016
+ "learning_rate": 8.661616161616161e-07,
1017
+ "loss": 0.5024,
1018
+ "step": 1430
1019
+ },
1020
+ {
1021
+ "epoch": 0.07,
1022
+ "grad_norm": 26.290699005126953,
1023
+ "learning_rate": 8.651515151515151e-07,
1024
+ "loss": 0.7017,
1025
+ "step": 1440
1026
+ },
1027
+ {
1028
+ "epoch": 0.07,
1029
+ "grad_norm": 23.3577880859375,
1030
+ "learning_rate": 8.641414141414141e-07,
1031
+ "loss": 0.6419,
1032
+ "step": 1450
1033
+ },
1034
+ {
1035
+ "epoch": 0.07,
1036
+ "grad_norm": 21.74049949645996,
1037
+ "learning_rate": 8.63131313131313e-07,
1038
+ "loss": 0.5426,
1039
+ "step": 1460
1040
+ },
1041
+ {
1042
+ "epoch": 0.07,
1043
+ "grad_norm": 0.5753927230834961,
1044
+ "learning_rate": 8.62121212121212e-07,
1045
+ "loss": 0.6417,
1046
+ "step": 1470
1047
+ },
1048
+ {
1049
+ "epoch": 0.07,
1050
+ "grad_norm": 36.96406936645508,
1051
+ "learning_rate": 8.611111111111111e-07,
1052
+ "loss": 0.6999,
1053
+ "step": 1480
1054
+ },
1055
+ {
1056
+ "epoch": 0.07,
1057
+ "grad_norm": 0.05758470296859741,
1058
+ "learning_rate": 8.601010101010102e-07,
1059
+ "loss": 0.816,
1060
+ "step": 1490
1061
+ },
1062
+ {
1063
+ "epoch": 0.07,
1064
+ "grad_norm": 51.20552062988281,
1065
+ "learning_rate": 8.590909090909091e-07,
1066
+ "loss": 0.7171,
1067
+ "step": 1500
1068
+ },
1069
+ {
1070
+ "epoch": 0.08,
1071
+ "grad_norm": 34.43236541748047,
1072
+ "learning_rate": 8.58080808080808e-07,
1073
+ "loss": 0.7448,
1074
+ "step": 1510
1075
+ },
1076
+ {
1077
+ "epoch": 0.08,
1078
+ "grad_norm": 89.9273681640625,
1079
+ "learning_rate": 8.570707070707071e-07,
1080
+ "loss": 0.6324,
1081
+ "step": 1520
1082
+ },
1083
+ {
1084
+ "epoch": 0.08,
1085
+ "grad_norm": 9.697078704833984,
1086
+ "learning_rate": 8.56060606060606e-07,
1087
+ "loss": 0.7951,
1088
+ "step": 1530
1089
+ },
1090
+ {
1091
+ "epoch": 0.08,
1092
+ "grad_norm": 28.903240203857422,
1093
+ "learning_rate": 8.55050505050505e-07,
1094
+ "loss": 0.6224,
1095
+ "step": 1540
1096
+ },
1097
+ {
1098
+ "epoch": 0.08,
1099
+ "grad_norm": 19.746826171875,
1100
+ "learning_rate": 8.54040404040404e-07,
1101
+ "loss": 0.4143,
1102
+ "step": 1550
1103
+ },
1104
+ {
1105
+ "epoch": 0.08,
1106
+ "grad_norm": 33.706146240234375,
1107
+ "learning_rate": 8.53030303030303e-07,
1108
+ "loss": 0.6803,
1109
+ "step": 1560
1110
+ },
1111
+ {
1112
+ "epoch": 0.08,
1113
+ "grad_norm": 24.144351959228516,
1114
+ "learning_rate": 8.52020202020202e-07,
1115
+ "loss": 0.6015,
1116
+ "step": 1570
1117
+ },
1118
+ {
1119
+ "epoch": 0.08,
1120
+ "grad_norm": 34.93477249145508,
1121
+ "learning_rate": 8.51010101010101e-07,
1122
+ "loss": 0.5599,
1123
+ "step": 1580
1124
+ },
1125
+ {
1126
+ "epoch": 0.08,
1127
+ "grad_norm": 31.863859176635742,
1128
+ "learning_rate": 8.499999999999999e-07,
1129
+ "loss": 0.7127,
1130
+ "step": 1590
1131
+ },
1132
+ {
1133
+ "epoch": 0.08,
1134
+ "grad_norm": 48.534549713134766,
1135
+ "learning_rate": 8.48989898989899e-07,
1136
+ "loss": 0.7777,
1137
+ "step": 1600
1138
+ },
1139
+ {
1140
+ "epoch": 0.08,
1141
+ "grad_norm": 35.08165740966797,
1142
+ "learning_rate": 8.479797979797979e-07,
1143
+ "loss": 0.6571,
1144
+ "step": 1610
1145
+ },
1146
+ {
1147
+ "epoch": 0.08,
1148
+ "grad_norm": 33.532325744628906,
1149
+ "learning_rate": 8.469696969696968e-07,
1150
+ "loss": 0.7386,
1151
+ "step": 1620
1152
+ },
1153
+ {
1154
+ "epoch": 0.08,
1155
+ "grad_norm": 0.014142200350761414,
1156
+ "learning_rate": 8.459595959595959e-07,
1157
+ "loss": 0.5505,
1158
+ "step": 1630
1159
+ },
1160
+ {
1161
+ "epoch": 0.08,
1162
+ "grad_norm": 29.99919319152832,
1163
+ "learning_rate": 8.449494949494948e-07,
1164
+ "loss": 0.4274,
1165
+ "step": 1640
1166
+ },
1167
+ {
1168
+ "epoch": 0.08,
1169
+ "grad_norm": 13.206497192382812,
1170
+ "learning_rate": 8.43939393939394e-07,
1171
+ "loss": 0.4399,
1172
+ "step": 1650
1173
+ },
1174
+ {
1175
+ "epoch": 0.08,
1176
+ "grad_norm": 17.408052444458008,
1177
+ "learning_rate": 8.429292929292929e-07,
1178
+ "loss": 0.5262,
1179
+ "step": 1660
1180
+ },
1181
+ {
1182
+ "epoch": 0.08,
1183
+ "grad_norm": 14.05802059173584,
1184
+ "learning_rate": 8.419191919191919e-07,
1185
+ "loss": 0.5503,
1186
+ "step": 1670
1187
+ },
1188
+ {
1189
+ "epoch": 0.08,
1190
+ "grad_norm": 13.401651382446289,
1191
+ "learning_rate": 8.409090909090909e-07,
1192
+ "loss": 0.813,
1193
+ "step": 1680
1194
+ },
1195
+ {
1196
+ "epoch": 0.08,
1197
+ "grad_norm": 28.40484619140625,
1198
+ "learning_rate": 8.398989898989899e-07,
1199
+ "loss": 0.7321,
1200
+ "step": 1690
1201
+ },
1202
+ {
1203
+ "epoch": 0.09,
1204
+ "grad_norm": 39.133670806884766,
1205
+ "learning_rate": 8.388888888888888e-07,
1206
+ "loss": 0.7129,
1207
+ "step": 1700
1208
+ },
1209
+ {
1210
+ "epoch": 0.09,
1211
+ "grad_norm": 26.99220848083496,
1212
+ "learning_rate": 8.378787878787879e-07,
1213
+ "loss": 0.645,
1214
+ "step": 1710
1215
+ },
1216
+ {
1217
+ "epoch": 0.09,
1218
+ "grad_norm": 22.875778198242188,
1219
+ "learning_rate": 8.368686868686868e-07,
1220
+ "loss": 0.6779,
1221
+ "step": 1720
1222
+ },
1223
+ {
1224
+ "epoch": 0.09,
1225
+ "grad_norm": 37.771705627441406,
1226
+ "learning_rate": 8.358585858585859e-07,
1227
+ "loss": 0.6104,
1228
+ "step": 1730
1229
+ },
1230
+ {
1231
+ "epoch": 0.09,
1232
+ "grad_norm": 17.48222541809082,
1233
+ "learning_rate": 8.348484848484848e-07,
1234
+ "loss": 0.5982,
1235
+ "step": 1740
1236
+ },
1237
+ {
1238
+ "epoch": 0.09,
1239
+ "grad_norm": 13.396077156066895,
1240
+ "learning_rate": 8.338383838383838e-07,
1241
+ "loss": 0.6295,
1242
+ "step": 1750
1243
+ },
1244
+ {
1245
+ "epoch": 0.09,
1246
+ "grad_norm": 48.97739791870117,
1247
+ "learning_rate": 8.328282828282828e-07,
1248
+ "loss": 0.8439,
1249
+ "step": 1760
1250
+ },
1251
+ {
1252
+ "epoch": 0.09,
1253
+ "grad_norm": 74.33853149414062,
1254
+ "learning_rate": 8.318181818181817e-07,
1255
+ "loss": 1.0566,
1256
+ "step": 1770
1257
+ },
1258
+ {
1259
+ "epoch": 0.09,
1260
+ "grad_norm": 7.2910051345825195,
1261
+ "learning_rate": 8.308080808080807e-07,
1262
+ "loss": 0.5226,
1263
+ "step": 1780
1264
+ },
1265
+ {
1266
+ "epoch": 0.09,
1267
+ "grad_norm": 27.389278411865234,
1268
+ "learning_rate": 8.297979797979797e-07,
1269
+ "loss": 1.1226,
1270
+ "step": 1790
1271
+ },
1272
+ {
1273
+ "epoch": 0.09,
1274
+ "grad_norm": 9.284111976623535,
1275
+ "learning_rate": 8.287878787878787e-07,
1276
+ "loss": 0.4101,
1277
+ "step": 1800
1278
+ },
1279
+ {
1280
+ "epoch": 0.09,
1281
+ "grad_norm": 8.962563514709473,
1282
+ "learning_rate": 8.277777777777777e-07,
1283
+ "loss": 0.5349,
1284
+ "step": 1810
1285
+ },
1286
+ {
1287
+ "epoch": 0.09,
1288
+ "grad_norm": 47.56216049194336,
1289
+ "learning_rate": 8.267676767676768e-07,
1290
+ "loss": 0.6863,
1291
+ "step": 1820
1292
+ },
1293
+ {
1294
+ "epoch": 0.09,
1295
+ "grad_norm": 31.547109603881836,
1296
+ "learning_rate": 8.257575757575757e-07,
1297
+ "loss": 0.7484,
1298
+ "step": 1830
1299
+ },
1300
+ {
1301
+ "epoch": 0.09,
1302
+ "grad_norm": 8.890266418457031,
1303
+ "learning_rate": 8.247474747474748e-07,
1304
+ "loss": 0.7518,
1305
+ "step": 1840
1306
+ },
1307
+ {
1308
+ "epoch": 0.09,
1309
+ "grad_norm": 25.44080352783203,
1310
+ "learning_rate": 8.237373737373737e-07,
1311
+ "loss": 0.8552,
1312
+ "step": 1850
1313
+ },
1314
+ {
1315
+ "epoch": 0.09,
1316
+ "grad_norm": 19.411556243896484,
1317
+ "learning_rate": 8.227272727272727e-07,
1318
+ "loss": 0.6285,
1319
+ "step": 1860
1320
+ },
1321
+ {
1322
+ "epoch": 0.09,
1323
+ "grad_norm": 5.5483574867248535,
1324
+ "learning_rate": 8.217171717171717e-07,
1325
+ "loss": 0.5478,
1326
+ "step": 1870
1327
+ },
1328
+ {
1329
+ "epoch": 0.09,
1330
+ "grad_norm": 22.145336151123047,
1331
+ "learning_rate": 8.207070707070707e-07,
1332
+ "loss": 0.7499,
1333
+ "step": 1880
1334
+ },
1335
+ {
1336
+ "epoch": 0.09,
1337
+ "grad_norm": 30.043731689453125,
1338
+ "learning_rate": 8.196969696969697e-07,
1339
+ "loss": 0.7252,
1340
+ "step": 1890
1341
+ },
1342
+ {
1343
+ "epoch": 0.1,
1344
+ "grad_norm": 39.9935417175293,
1345
+ "learning_rate": 8.186868686868687e-07,
1346
+ "loss": 0.7348,
1347
+ "step": 1900
1348
+ },
1349
+ {
1350
+ "epoch": 0.1,
1351
+ "grad_norm": 5.8807525634765625,
1352
+ "learning_rate": 8.176767676767676e-07,
1353
+ "loss": 0.381,
1354
+ "step": 1910
1355
+ },
1356
+ {
1357
+ "epoch": 0.1,
1358
+ "grad_norm": 16.082597732543945,
1359
+ "learning_rate": 8.166666666666666e-07,
1360
+ "loss": 0.6413,
1361
+ "step": 1920
1362
+ },
1363
+ {
1364
+ "epoch": 0.1,
1365
+ "grad_norm": 15.713370323181152,
1366
+ "learning_rate": 8.156565656565656e-07,
1367
+ "loss": 0.4765,
1368
+ "step": 1930
1369
+ },
1370
+ {
1371
+ "epoch": 0.1,
1372
+ "grad_norm": 43.45647048950195,
1373
+ "learning_rate": 8.146464646464645e-07,
1374
+ "loss": 0.6653,
1375
+ "step": 1940
1376
+ },
1377
+ {
1378
+ "epoch": 0.1,
1379
+ "grad_norm": 51.137046813964844,
1380
+ "learning_rate": 8.136363636363636e-07,
1381
+ "loss": 0.6915,
1382
+ "step": 1950
1383
+ },
1384
+ {
1385
+ "epoch": 0.1,
1386
+ "grad_norm": 33.2936897277832,
1387
+ "learning_rate": 8.126262626262625e-07,
1388
+ "loss": 0.4993,
1389
+ "step": 1960
1390
+ },
1391
+ {
1392
+ "epoch": 0.1,
1393
+ "grad_norm": 10.87304973602295,
1394
+ "learning_rate": 8.116161616161616e-07,
1395
+ "loss": 0.7893,
1396
+ "step": 1970
1397
+ },
1398
+ {
1399
+ "epoch": 0.1,
1400
+ "grad_norm": 0.774446427822113,
1401
+ "learning_rate": 8.106060606060605e-07,
1402
+ "loss": 0.5946,
1403
+ "step": 1980
1404
+ },
1405
+ {
1406
+ "epoch": 0.1,
1407
+ "grad_norm": 26.221094131469727,
1408
+ "learning_rate": 8.095959595959596e-07,
1409
+ "loss": 0.8534,
1410
+ "step": 1990
1411
+ },
1412
+ {
1413
+ "epoch": 0.1,
1414
+ "grad_norm": 46.51724624633789,
1415
+ "learning_rate": 8.085858585858586e-07,
1416
+ "loss": 0.4862,
1417
+ "step": 2000
1418
+ },
1419
+ {
1420
+ "epoch": 0.1,
1421
+ "eval_loss": 0.6236868500709534,
1422
+ "eval_runtime": 274.2428,
1423
+ "eval_samples_per_second": 3.646,
1424
+ "eval_steps_per_second": 3.646,
1425
+ "step": 2000
1426
+ }
1427
+ ],
1428
+ "logging_steps": 10,
1429
+ "max_steps": 10000,
1430
+ "num_input_tokens_seen": 0,
1431
+ "num_train_epochs": 1,
1432
+ "save_steps": 2000,
1433
+ "total_flos": 9.4282098671616e+16,
1434
+ "train_batch_size": 1,
1435
+ "trial_name": null,
1436
+ "trial_params": null
1437
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01a8cb5e2b6b3a37c7865550e33535f27e6d809c12560726f8d0484265c26dae
3
+ size 4856