Sparx3d commited on
Commit
b60c05c
·
verified ·
1 Parent(s): 278e5c8

Upload folder using huggingface_hub

Browse files
README.md CHANGED
@@ -1,3 +1,202 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: nvidia/GR00T-N1-2B
3
+ library_name: peft
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 0.14.0
adapter_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/root/.cache/huggingface/hub/models--nvidia--GR00T-N1-2B/snapshots/32e1fd2507f7739fad443e6b449c8188e0e02fcb",
5
+ "bias": "none",
6
+ "eva_config": null,
7
+ "exclude_modules": null,
8
+ "fan_in_fan_out": false,
9
+ "inference_mode": true,
10
+ "init_lora_weights": true,
11
+ "layer_replication": null,
12
+ "layers_pattern": null,
13
+ "layers_to_transform": null,
14
+ "loftq_config": {},
15
+ "lora_alpha": 128,
16
+ "lora_bias": false,
17
+ "lora_dropout": 0.1,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 64,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "to_q",
27
+ "q_proj",
28
+ "to_v",
29
+ "v_proj",
30
+ "to_k",
31
+ "k_proj"
32
+ ],
33
+ "task_type": "CAUSAL_LM",
34
+ "use_dora": false,
35
+ "use_rslora": false
36
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12e92d22f48dff8407cc37f610b1b7a4af227cb792b25a76f6fd4132e955eb02
3
+ size 123328576
experiment_cfg/metadata.json ADDED
@@ -0,0 +1,203 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "new_embodiment": {
3
+ "statistics": {
4
+ "state": {
5
+ "single_arm": {
6
+ "max": [
7
+ 1.3256829977035522,
8
+ 1.6831878423690796,
9
+ 1.6018670797348022,
10
+ 1.6540350914001465,
11
+ 0.19793184101581573
12
+ ],
13
+ "min": [
14
+ -1.350232720375061,
15
+ -1.8304859399795532,
16
+ -1.3625075817108154,
17
+ -1.8488982915878296,
18
+ -0.13809198141098022
19
+ ],
20
+ "mean": [
21
+ -0.21111595630645752,
22
+ -0.37636134028434753,
23
+ 0.8651418685913086,
24
+ -0.8441829681396484,
25
+ 0.04267279431223869
26
+ ],
27
+ "std": [
28
+ 0.6699364185333252,
29
+ 1.0180519819259644,
30
+ 0.8384478092193604,
31
+ 0.5619941353797913,
32
+ 0.0544276125729084
33
+ ],
34
+ "q01": [
35
+ -1.3241486549377441,
36
+ -1.7844552993774414,
37
+ -1.3042020797729492,
38
+ -1.6939283609390259,
39
+ -0.13655762374401093
40
+ ],
41
+ "q99": [
42
+ 1.2980647087097168,
43
+ 1.480652928352356,
44
+ 1.6003326177597046,
45
+ 1.3333548307418823,
46
+ 0.15957295894622803
47
+ ]
48
+ },
49
+ "gripper": {
50
+ "max": [
51
+ 2.0713796615600586
52
+ ],
53
+ "min": [
54
+ 0.009206132031977177
55
+ ],
56
+ "mean": [
57
+ 0.322316437959671
58
+ ],
59
+ "std": [
60
+ 0.5169613361358643
61
+ ],
62
+ "q01": [
63
+ 0.009206132031977177
64
+ ],
65
+ "q99": [
66
+ 1.7307528257369995
67
+ ]
68
+ }
69
+ },
70
+ "action": {
71
+ "single_arm": {
72
+ "max": [
73
+ 1.3256829977035522,
74
+ 1.6831878423690796,
75
+ 1.6018670797348022,
76
+ 1.6540350914001465,
77
+ 0.19793184101581573
78
+ ],
79
+ "min": [
80
+ -1.350232720375061,
81
+ -1.8304859399795532,
82
+ -1.3625075817108154,
83
+ -1.8488982915878296,
84
+ -0.13809198141098022
85
+ ],
86
+ "mean": [
87
+ -0.21111606061458588,
88
+ -0.3763605058193207,
89
+ 0.8651413917541504,
90
+ -0.8441831469535828,
91
+ 0.04267395660281181
92
+ ],
93
+ "std": [
94
+ 0.6699364185333252,
95
+ 1.018051028251648,
96
+ 0.838447630405426,
97
+ 0.5619938969612122,
98
+ 0.054428581148386
99
+ ],
100
+ "q01": [
101
+ -1.3241486549377441,
102
+ -1.7844552993774414,
103
+ -1.3042020797729492,
104
+ -1.6939283609390259,
105
+ -0.13655762374401093
106
+ ],
107
+ "q99": [
108
+ 1.2980647087097168,
109
+ 1.480652928352356,
110
+ 1.6003326177597046,
111
+ 1.3333548307418823,
112
+ 0.15957295894622803
113
+ ]
114
+ },
115
+ "gripper": {
116
+ "max": [
117
+ 2.0713796615600586
118
+ ],
119
+ "min": [
120
+ 0.009206132031977177
121
+ ],
122
+ "mean": [
123
+ 0.32231196761131287
124
+ ],
125
+ "std": [
126
+ 0.5169665813446045
127
+ ],
128
+ "q01": [
129
+ 0.009206132031977177
130
+ ],
131
+ "q99": [
132
+ 1.7307528257369995
133
+ ]
134
+ }
135
+ }
136
+ },
137
+ "modalities": {
138
+ "video": {
139
+ "main": {
140
+ "resolution": [
141
+ 320,
142
+ 240
143
+ ],
144
+ "channels": 3,
145
+ "fps": 30.0
146
+ },
147
+ "secondary_0": {
148
+ "resolution": [
149
+ 320,
150
+ 240
151
+ ],
152
+ "channels": 3,
153
+ "fps": 30.0
154
+ },
155
+ "secondary_1": {
156
+ "resolution": [
157
+ 320,
158
+ 240
159
+ ],
160
+ "channels": 3,
161
+ "fps": 30.0
162
+ }
163
+ },
164
+ "state": {
165
+ "single_arm": {
166
+ "absolute": true,
167
+ "rotation_type": null,
168
+ "shape": [
169
+ 5
170
+ ],
171
+ "continuous": true
172
+ },
173
+ "gripper": {
174
+ "absolute": true,
175
+ "rotation_type": null,
176
+ "shape": [
177
+ 1
178
+ ],
179
+ "continuous": true
180
+ }
181
+ },
182
+ "action": {
183
+ "single_arm": {
184
+ "absolute": true,
185
+ "rotation_type": null,
186
+ "shape": [
187
+ 5
188
+ ],
189
+ "continuous": true
190
+ },
191
+ "gripper": {
192
+ "absolute": true,
193
+ "rotation_type": null,
194
+ "shape": [
195
+ 1
196
+ ],
197
+ "continuous": true
198
+ }
199
+ }
200
+ },
201
+ "embodiment_tag": "new_embodiment"
202
+ }
203
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a523ad8dc9a069c3050531ba45bb3d7ee500f4a826779cff7a5626279ae926f0
3
+ size 246824634
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7de0bc89615aaf6a6ee78f1d06925ed7d331eee501d3484ea259c3a244333f49
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe1d153de177b356f9e3a70d6e4ec979560b0c300994e71ca4cb89afc74c5b3a
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,383 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.16852039096730703,
5
+ "eval_steps": 500,
6
+ "global_step": 500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.003370407819346141,
13
+ "grad_norm": 0.6622726321220398,
14
+ "learning_rate": 4e-05,
15
+ "loss": 1.1086,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.006740815638692282,
20
+ "grad_norm": 0.6852302551269531,
21
+ "learning_rate": 8e-05,
22
+ "loss": 1.0139,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.010111223458038422,
27
+ "grad_norm": 0.7799952626228333,
28
+ "learning_rate": 9.997266286704631e-05,
29
+ "loss": 0.7389,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.013481631277384564,
34
+ "grad_norm": 1.3821028470993042,
35
+ "learning_rate": 9.975414512725057e-05,
36
+ "loss": 0.4005,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.016852039096730706,
41
+ "grad_norm": 1.4913556575775146,
42
+ "learning_rate": 9.931806517013612e-05,
43
+ "loss": 0.5061,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.020222446916076844,
48
+ "grad_norm": 1.5664910078048706,
49
+ "learning_rate": 9.86663298624003e-05,
50
+ "loss": 0.4028,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.023592854735422986,
55
+ "grad_norm": 1.2872231006622314,
56
+ "learning_rate": 9.780178907671789e-05,
57
+ "loss": 0.3596,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.026963262554769128,
62
+ "grad_norm": 1.8300050497055054,
63
+ "learning_rate": 9.672822322997305e-05,
64
+ "loss": 0.3788,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.030333670374115267,
69
+ "grad_norm": 1.0094068050384521,
70
+ "learning_rate": 9.545032675245813e-05,
71
+ "loss": 0.3413,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.03370407819346141,
76
+ "grad_norm": 1.8348039388656616,
77
+ "learning_rate": 9.397368756032445e-05,
78
+ "loss": 0.3873,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.03707448601280755,
83
+ "grad_norm": 0.6941381692886353,
84
+ "learning_rate": 9.230476262104677e-05,
85
+ "loss": 0.2787,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.04044489383215369,
90
+ "grad_norm": 1.146726131439209,
91
+ "learning_rate": 9.045084971874738e-05,
92
+ "loss": 0.3802,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.043815301651499834,
97
+ "grad_norm": 1.0894972085952759,
98
+ "learning_rate": 8.842005554284296e-05,
99
+ "loss": 0.3474,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.04718570947084597,
104
+ "grad_norm": 1.1947873830795288,
105
+ "learning_rate": 8.622126023955446e-05,
106
+ "loss": 0.303,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.05055611729019211,
111
+ "grad_norm": 0.881015419960022,
112
+ "learning_rate": 8.386407858128706e-05,
113
+ "loss": 0.3656,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.053926525109538256,
118
+ "grad_norm": 0.44869264960289,
119
+ "learning_rate": 8.135881792367686e-05,
120
+ "loss": 0.3268,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.057296932928884395,
125
+ "grad_norm": 1.1546025276184082,
126
+ "learning_rate": 7.871643313414718e-05,
127
+ "loss": 0.3123,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.06066734074823053,
132
+ "grad_norm": 0.6667796969413757,
133
+ "learning_rate": 7.594847868906076e-05,
134
+ "loss": 0.3069,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.06403774856757667,
139
+ "grad_norm": 1.3780990839004517,
140
+ "learning_rate": 7.30670581489344e-05,
141
+ "loss": 0.2845,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.06740815638692282,
146
+ "grad_norm": 1.0180288553237915,
147
+ "learning_rate": 7.008477123264848e-05,
148
+ "loss": 0.2592,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.07077856420626896,
153
+ "grad_norm": 0.7397503852844238,
154
+ "learning_rate": 6.701465872208216e-05,
155
+ "loss": 0.2507,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.0741489720256151,
160
+ "grad_norm": 0.6356308460235596,
161
+ "learning_rate": 6.387014543809223e-05,
162
+ "loss": 0.3174,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.07751937984496124,
167
+ "grad_norm": 1.1012778282165527,
168
+ "learning_rate": 6.066498153718735e-05,
169
+ "loss": 0.2273,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.08088978766430738,
174
+ "grad_norm": 0.9452115297317505,
175
+ "learning_rate": 5.74131823855921e-05,
176
+ "loss": 0.2841,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.08426019548365352,
181
+ "grad_norm": 1.153079867362976,
182
+ "learning_rate": 5.4128967273616625e-05,
183
+ "loss": 0.2687,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.08763060330299967,
188
+ "grad_norm": 0.485048770904541,
189
+ "learning_rate": 5.0826697238317935e-05,
190
+ "loss": 0.2322,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.0910010111223458,
195
+ "grad_norm": 0.4272606372833252,
196
+ "learning_rate": 4.7520812266338885e-05,
197
+ "loss": 0.1996,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.09437141894169195,
202
+ "grad_norm": 0.9538323879241943,
203
+ "learning_rate": 4.4225768151520694e-05,
204
+ "loss": 0.2667,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.09774182676103808,
209
+ "grad_norm": 1.2973414659500122,
210
+ "learning_rate": 4.095597328339452e-05,
211
+ "loss": 0.274,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.10111223458038422,
216
+ "grad_norm": 0.9469539523124695,
217
+ "learning_rate": 3.772572564296005e-05,
218
+ "loss": 0.2769,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.10448264239973036,
223
+ "grad_norm": 0.8325055241584778,
224
+ "learning_rate": 3.4549150281252636e-05,
225
+ "loss": 0.1807,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.10785305021907651,
230
+ "grad_norm": 1.1702295541763306,
231
+ "learning_rate": 3.144013755408895e-05,
232
+ "loss": 0.2512,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.11122345803842265,
237
+ "grad_norm": 0.5195464491844177,
238
+ "learning_rate": 2.8412282383075363e-05,
239
+ "loss": 0.2479,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.11459386585776879,
244
+ "grad_norm": 1.5858228206634521,
245
+ "learning_rate": 2.547882480847461e-05,
246
+ "loss": 0.2569,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.11796427367711493,
251
+ "grad_norm": 0.6920508742332458,
252
+ "learning_rate": 2.2652592093878666e-05,
253
+ "loss": 0.2354,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.12133468149646107,
258
+ "grad_norm": 0.9595134258270264,
259
+ "learning_rate": 1.9945942635848748e-05,
260
+ "loss": 0.2104,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.12470508931580722,
265
+ "grad_norm": 0.80647873878479,
266
+ "learning_rate": 1.7370711923791567e-05,
267
+ "loss": 0.2296,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.12807549713515334,
272
+ "grad_norm": 1.2443121671676636,
273
+ "learning_rate": 1.4938160786375572e-05,
274
+ "loss": 0.2175,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.13144590495449948,
279
+ "grad_norm": 1.084061861038208,
280
+ "learning_rate": 1.2658926150792322e-05,
281
+ "loss": 0.3018,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.13481631277384565,
286
+ "grad_norm": 1.718507170677185,
287
+ "learning_rate": 1.0542974530180327e-05,
288
+ "loss": 0.2336,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.1381867205931918,
293
+ "grad_norm": 1.6592141389846802,
294
+ "learning_rate": 8.599558442598998e-06,
295
+ "loss": 0.2068,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.14155712841253792,
300
+ "grad_norm": 0.9472789764404297,
301
+ "learning_rate": 6.837175952121306e-06,
302
+ "loss": 0.2019,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.14492753623188406,
307
+ "grad_norm": 0.6342177987098694,
308
+ "learning_rate": 5.263533508961827e-06,
309
+ "loss": 0.207,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.1482979440512302,
314
+ "grad_norm": 1.4079145193099976,
315
+ "learning_rate": 3.885512251130763e-06,
316
+ "loss": 0.2979,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.15166835187057634,
321
+ "grad_norm": 1.145531415939331,
322
+ "learning_rate": 2.7091379149682685e-06,
323
+ "loss": 0.195,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.15503875968992248,
328
+ "grad_norm": 1.4974510669708252,
329
+ "learning_rate": 1.7395544861325718e-06,
330
+ "loss": 0.2252,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.15840916750926862,
335
+ "grad_norm": 1.1619243621826172,
336
+ "learning_rate": 9.810017062595322e-07,
337
+ "loss": 0.2068,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.16177957532861476,
342
+ "grad_norm": 0.5374842286109924,
343
+ "learning_rate": 4.367965336512403e-07,
344
+ "loss": 0.2431,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.1651499831479609,
349
+ "grad_norm": 1.352457880973816,
350
+ "learning_rate": 1.0931863906127327e-07,
351
+ "loss": 0.2363,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.16852039096730703,
356
+ "grad_norm": 1.1476552486419678,
357
+ "learning_rate": 0.0,
358
+ "loss": 0.1907,
359
+ "step": 500
360
+ }
361
+ ],
362
+ "logging_steps": 10,
363
+ "max_steps": 500,
364
+ "num_input_tokens_seen": 0,
365
+ "num_train_epochs": 1,
366
+ "save_steps": 500,
367
+ "stateful_callbacks": {
368
+ "TrainerControl": {
369
+ "args": {
370
+ "should_epoch_stop": false,
371
+ "should_evaluate": false,
372
+ "should_log": false,
373
+ "should_save": true,
374
+ "should_training_stop": true
375
+ },
376
+ "attributes": {}
377
+ }
378
+ },
379
+ "total_flos": 6303999518208000.0,
380
+ "train_batch_size": 4,
381
+ "trial_name": null,
382
+ "trial_params": null
383
+ }