Fill-Mask
PEFT
Safetensors
Transformers
modernbert
lora
dapt
sft
heitorrosa commited on
Commit
39e237f
·
verified ·
1 Parent(s): 1679dae

Upload folder using huggingface_hub

Browse files
sft/checkpoint-1650/README.md ADDED
@@ -0,0 +1,206 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: heitorrosa/logun-base
3
+ library_name: peft
4
+ tags:
5
+ - base_model:adapter:heitorrosa/logun-base
6
+ - lora
7
+ - transformers
8
+ ---
9
+
10
+ # Model Card for Model ID
11
+
12
+ <!-- Provide a quick summary of what the model is/does. -->
13
+
14
+
15
+
16
+ ## Model Details
17
+
18
+ ### Model Description
19
+
20
+ <!-- Provide a longer summary of what this model is. -->
21
+
22
+
23
+
24
+ - **Developed by:** [More Information Needed]
25
+ - **Funded by [optional]:** [More Information Needed]
26
+ - **Shared by [optional]:** [More Information Needed]
27
+ - **Model type:** [More Information Needed]
28
+ - **Language(s) (NLP):** [More Information Needed]
29
+ - **License:** [More Information Needed]
30
+ - **Finetuned from model [optional]:** [More Information Needed]
31
+
32
+ ### Model Sources [optional]
33
+
34
+ <!-- Provide the basic links for the model. -->
35
+
36
+ - **Repository:** [More Information Needed]
37
+ - **Paper [optional]:** [More Information Needed]
38
+ - **Demo [optional]:** [More Information Needed]
39
+
40
+ ## Uses
41
+
42
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
43
+
44
+ ### Direct Use
45
+
46
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
47
+
48
+ [More Information Needed]
49
+
50
+ ### Downstream Use [optional]
51
+
52
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
53
+
54
+ [More Information Needed]
55
+
56
+ ### Out-of-Scope Use
57
+
58
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
59
+
60
+ [More Information Needed]
61
+
62
+ ## Bias, Risks, and Limitations
63
+
64
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
65
+
66
+ [More Information Needed]
67
+
68
+ ### Recommendations
69
+
70
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
71
+
72
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
73
+
74
+ ## How to Get Started with the Model
75
+
76
+ Use the code below to get started with the model.
77
+
78
+ [More Information Needed]
79
+
80
+ ## Training Details
81
+
82
+ ### Training Data
83
+
84
+ <!-- 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. -->
85
+
86
+ [More Information Needed]
87
+
88
+ ### Training Procedure
89
+
90
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
91
+
92
+ #### Preprocessing [optional]
93
+
94
+ [More Information Needed]
95
+
96
+
97
+ #### Training Hyperparameters
98
+
99
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
100
+
101
+ #### Speeds, Sizes, Times [optional]
102
+
103
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
104
+
105
+ [More Information Needed]
106
+
107
+ ## Evaluation
108
+
109
+ <!-- This section describes the evaluation protocols and provides the results. -->
110
+
111
+ ### Testing Data, Factors & Metrics
112
+
113
+ #### Testing Data
114
+
115
+ <!-- This should link to a Dataset Card if possible. -->
116
+
117
+ [More Information Needed]
118
+
119
+ #### Factors
120
+
121
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
122
+
123
+ [More Information Needed]
124
+
125
+ #### Metrics
126
+
127
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
128
+
129
+ [More Information Needed]
130
+
131
+ ### Results
132
+
133
+ [More Information Needed]
134
+
135
+ #### Summary
136
+
137
+
138
+
139
+ ## Model Examination [optional]
140
+
141
+ <!-- Relevant interpretability work for the model goes here -->
142
+
143
+ [More Information Needed]
144
+
145
+ ## Environmental Impact
146
+
147
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
148
+
149
+ 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).
150
+
151
+ - **Hardware Type:** [More Information Needed]
152
+ - **Hours used:** [More Information Needed]
153
+ - **Cloud Provider:** [More Information Needed]
154
+ - **Compute Region:** [More Information Needed]
155
+ - **Carbon Emitted:** [More Information Needed]
156
+
157
+ ## Technical Specifications [optional]
158
+
159
+ ### Model Architecture and Objective
160
+
161
+ [More Information Needed]
162
+
163
+ ### Compute Infrastructure
164
+
165
+ [More Information Needed]
166
+
167
+ #### Hardware
168
+
169
+ [More Information Needed]
170
+
171
+ #### Software
172
+
173
+ [More Information Needed]
174
+
175
+ ## Citation [optional]
176
+
177
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
178
+
179
+ **BibTeX:**
180
+
181
+ [More Information Needed]
182
+
183
+ **APA:**
184
+
185
+ [More Information Needed]
186
+
187
+ ## Glossary [optional]
188
+
189
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
190
+
191
+ [More Information Needed]
192
+
193
+ ## More Information [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Authors [optional]
198
+
199
+ [More Information Needed]
200
+
201
+ ## Model Card Contact
202
+
203
+ [More Information Needed]
204
+ ### Framework versions
205
+
206
+ - PEFT 0.20.0
sft/checkpoint-1650/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc2272777d1c8fae666fdc725fa39bf09ebb0beccca2bb09bfae018e44e855d0
3
+ size 27204427
sft/checkpoint-1650/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d3051b6fc4b6bba34e77747ee8ec4a8dead57a5a0da4f5e330add1c840445cd
3
+ size 14917
sft/checkpoint-1650/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a132fd7b4ba58ab88966f515d4b4b281ebeaa395e1ebe8511c0c48af85a2bb9
3
+ size 1383
sft/checkpoint-1650/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44a321509eb550d67a5dc87b0779109a2a0b35303b3f97a56fb998ae3efca59d
3
+ size 1465
sft/checkpoint-1650/sft/adapter_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "heitorrosa/logun-base",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 32,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.05,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": [
26
+ "classifier",
27
+ "classifier",
28
+ "score"
29
+ ],
30
+ "monteclora_config": null,
31
+ "peft_type": "LORA",
32
+ "peft_version": "0.20.0",
33
+ "qalora_group_size": 16,
34
+ "r": 16,
35
+ "rank_pattern": {},
36
+ "revision": null,
37
+ "target_modules": [
38
+ "Wqkv",
39
+ "Wo",
40
+ "Wi"
41
+ ],
42
+ "target_parameters": null,
43
+ "task_type": "SEQ_CLS",
44
+ "trainable_token_indices": null,
45
+ "use_bdlora": null,
46
+ "use_dora": false,
47
+ "use_qalora": false,
48
+ "use_rslora": false,
49
+ "velora_config": null
50
+ }
sft/checkpoint-1650/sft/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:deea94d43827e9d87987291d87e6f77560148bf7e5b0bd50cd96f9231cd5c5da
3
+ size 13547940
sft/checkpoint-1650/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
sft/checkpoint-1650/tokenizer_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "[CLS]",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "[SEP]",
6
+ "is_local": false,
7
+ "local_files_only": false,
8
+ "mask_token": "[MASK]",
9
+ "model_input_names": [
10
+ "input_ids",
11
+ "attention_mask"
12
+ ],
13
+ "model_max_length": 8192,
14
+ "pad_token": "[PAD]",
15
+ "padding_side": "right",
16
+ "tokenizer_class": "TokenizersBackend",
17
+ "truncation_side": "right",
18
+ "unk_token": "[UNK]"
19
+ }
sft/checkpoint-1650/trainer_state.json ADDED
@@ -0,0 +1,914 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0900035157623345,
6
+ "eval_steps": 150,
7
+ "global_step": 1650,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.02812609867572952,
14
+ "grad_norm": NaN,
15
+ "learning_rate": 4.666666666666667e-06,
16
+ "loss": 40.91645100911458,
17
+ "step": 15
18
+ },
19
+ {
20
+ "epoch": 0.05625219735145904,
21
+ "grad_norm": 108.49263000488281,
22
+ "learning_rate": 9.666666666666667e-06,
23
+ "loss": 38.68733317057292,
24
+ "step": 30
25
+ },
26
+ {
27
+ "epoch": 0.08437829602718856,
28
+ "grad_norm": 87.13339233398438,
29
+ "learning_rate": 1.4666666666666668e-05,
30
+ "loss": 37.54708658854167,
31
+ "step": 45
32
+ },
33
+ {
34
+ "epoch": 0.11250439470291808,
35
+ "grad_norm": 82.61961364746094,
36
+ "learning_rate": 1.9666666666666666e-05,
37
+ "loss": 35.59373372395833,
38
+ "step": 60
39
+ },
40
+ {
41
+ "epoch": 0.1406304933786476,
42
+ "grad_norm": 94.90762329101562,
43
+ "learning_rate": 2.466666666666667e-05,
44
+ "loss": 34.33445638020833,
45
+ "step": 75
46
+ },
47
+ {
48
+ "epoch": 0.16875659205437712,
49
+ "grad_norm": 64.12799072265625,
50
+ "learning_rate": 2.9666666666666672e-05,
51
+ "loss": 33.768391927083336,
52
+ "step": 90
53
+ },
54
+ {
55
+ "epoch": 0.19688269073010664,
56
+ "grad_norm": 61.35285568237305,
57
+ "learning_rate": 3.466666666666667e-05,
58
+ "loss": 33.065120442708334,
59
+ "step": 105
60
+ },
61
+ {
62
+ "epoch": 0.22500878940583616,
63
+ "grad_norm": 56.75034713745117,
64
+ "learning_rate": 3.966666666666667e-05,
65
+ "loss": 32.87635091145833,
66
+ "step": 120
67
+ },
68
+ {
69
+ "epoch": 0.2531348880815657,
70
+ "grad_norm": 88.83663177490234,
71
+ "learning_rate": 4.466666666666667e-05,
72
+ "loss": 31.945328776041666,
73
+ "step": 135
74
+ },
75
+ {
76
+ "epoch": 0.2812609867572952,
77
+ "grad_norm": 53.496788024902344,
78
+ "learning_rate": 4.966666666666667e-05,
79
+ "loss": 32.28165283203125,
80
+ "step": 150
81
+ },
82
+ {
83
+ "epoch": 0.2812609867572952,
84
+ "eval_accuracy": 0.4985507246376812,
85
+ "eval_loss": 1.9326186180114746,
86
+ "eval_macro_f1": 0.4513996326113265,
87
+ "eval_runtime": 7.0971,
88
+ "eval_samples_per_second": 48.611,
89
+ "eval_steps_per_second": 6.2,
90
+ "step": 150
91
+ },
92
+ {
93
+ "epoch": 0.30938708543302473,
94
+ "grad_norm": 54.809783935546875,
95
+ "learning_rate": 4.9830179524502674e-05,
96
+ "loss": 30.544930013020835,
97
+ "step": 165
98
+ },
99
+ {
100
+ "epoch": 0.33751318410875425,
101
+ "grad_norm": 68.34676361083984,
102
+ "learning_rate": 4.964822901504124e-05,
103
+ "loss": 29.883894856770834,
104
+ "step": 180
105
+ },
106
+ {
107
+ "epoch": 0.36563928278448377,
108
+ "grad_norm": 70.30874633789062,
109
+ "learning_rate": 4.9466278505579815e-05,
110
+ "loss": 29.711442057291666,
111
+ "step": 195
112
+ },
113
+ {
114
+ "epoch": 0.3937653814602133,
115
+ "grad_norm": 105.4150161743164,
116
+ "learning_rate": 4.928432799611839e-05,
117
+ "loss": 29.863224283854166,
118
+ "step": 210
119
+ },
120
+ {
121
+ "epoch": 0.4218914801359428,
122
+ "grad_norm": 81.67976379394531,
123
+ "learning_rate": 4.910237748665696e-05,
124
+ "loss": 29.67599080403646,
125
+ "step": 225
126
+ },
127
+ {
128
+ "epoch": 0.4500175788116723,
129
+ "grad_norm": 78.1202621459961,
130
+ "learning_rate": 4.8920426977195536e-05,
131
+ "loss": 28.802783203125,
132
+ "step": 240
133
+ },
134
+ {
135
+ "epoch": 0.47814367748740183,
136
+ "grad_norm": 73.63782501220703,
137
+ "learning_rate": 4.873847646773411e-05,
138
+ "loss": 27.798103841145835,
139
+ "step": 255
140
+ },
141
+ {
142
+ "epoch": 0.5062697761631314,
143
+ "grad_norm": 77.5123519897461,
144
+ "learning_rate": 4.855652595827268e-05,
145
+ "loss": 26.746952311197916,
146
+ "step": 270
147
+ },
148
+ {
149
+ "epoch": 0.5343958748388609,
150
+ "grad_norm": 70.0318603515625,
151
+ "learning_rate": 4.837457544881126e-05,
152
+ "loss": 26.3315673828125,
153
+ "step": 285
154
+ },
155
+ {
156
+ "epoch": 0.5625219735145904,
157
+ "grad_norm": 66.42996215820312,
158
+ "learning_rate": 4.819262493934984e-05,
159
+ "loss": 26.488555908203125,
160
+ "step": 300
161
+ },
162
+ {
163
+ "epoch": 0.5625219735145904,
164
+ "eval_accuracy": 0.6318840579710145,
165
+ "eval_loss": 1.615958333015442,
166
+ "eval_macro_f1": 0.6129856465867943,
167
+ "eval_runtime": 2.3114,
168
+ "eval_samples_per_second": 149.263,
169
+ "eval_steps_per_second": 19.036,
170
+ "step": 300
171
+ },
172
+ {
173
+ "epoch": 0.5906480721903199,
174
+ "grad_norm": 68.63166046142578,
175
+ "learning_rate": 4.801067442988841e-05,
176
+ "loss": 26.851969401041668,
177
+ "step": 315
178
+ },
179
+ {
180
+ "epoch": 0.6187741708660495,
181
+ "grad_norm": 94.37174224853516,
182
+ "learning_rate": 4.7828723920426985e-05,
183
+ "loss": 26.854146321614582,
184
+ "step": 330
185
+ },
186
+ {
187
+ "epoch": 0.6469002695417789,
188
+ "grad_norm": 85.5411605834961,
189
+ "learning_rate": 4.764677341096555e-05,
190
+ "loss": 24.6757080078125,
191
+ "step": 345
192
+ },
193
+ {
194
+ "epoch": 0.6750263682175085,
195
+ "grad_norm": 64.81537628173828,
196
+ "learning_rate": 4.7464822901504125e-05,
197
+ "loss": 27.398944091796874,
198
+ "step": 360
199
+ },
200
+ {
201
+ "epoch": 0.7031524668932381,
202
+ "grad_norm": 98.3795394897461,
203
+ "learning_rate": 4.72828723920427e-05,
204
+ "loss": 25.361378987630207,
205
+ "step": 375
206
+ },
207
+ {
208
+ "epoch": 0.7312785655689675,
209
+ "grad_norm": 60.86552810668945,
210
+ "learning_rate": 4.710092188258127e-05,
211
+ "loss": 23.455232747395833,
212
+ "step": 390
213
+ },
214
+ {
215
+ "epoch": 0.7594046642446971,
216
+ "grad_norm": 65.06398010253906,
217
+ "learning_rate": 4.6918971373119846e-05,
218
+ "loss": 25.147119140625,
219
+ "step": 405
220
+ },
221
+ {
222
+ "epoch": 0.7875307629204266,
223
+ "grad_norm": 64.24246978759766,
224
+ "learning_rate": 4.673702086365842e-05,
225
+ "loss": 26.254545084635417,
226
+ "step": 420
227
+ },
228
+ {
229
+ "epoch": 0.8156568615961561,
230
+ "grad_norm": 85.69407653808594,
231
+ "learning_rate": 4.6555070354196993e-05,
232
+ "loss": 25.228023274739584,
233
+ "step": 435
234
+ },
235
+ {
236
+ "epoch": 0.8437829602718856,
237
+ "grad_norm": 91.77117919921875,
238
+ "learning_rate": 4.637311984473557e-05,
239
+ "loss": 24.674845377604168,
240
+ "step": 450
241
+ },
242
+ {
243
+ "epoch": 0.8437829602718856,
244
+ "eval_accuracy": 0.6579710144927536,
245
+ "eval_loss": 1.529452919960022,
246
+ "eval_macro_f1": 0.6434151685975086,
247
+ "eval_runtime": 2.2932,
248
+ "eval_samples_per_second": 150.442,
249
+ "eval_steps_per_second": 19.187,
250
+ "step": 450
251
+ },
252
+ {
253
+ "epoch": 0.8719090589476152,
254
+ "grad_norm": 59.32505798339844,
255
+ "learning_rate": 4.619116933527414e-05,
256
+ "loss": 25.152834065755208,
257
+ "step": 465
258
+ },
259
+ {
260
+ "epoch": 0.9000351576233446,
261
+ "grad_norm": 68.90987396240234,
262
+ "learning_rate": 4.6009218825812714e-05,
263
+ "loss": 23.644384765625,
264
+ "step": 480
265
+ },
266
+ {
267
+ "epoch": 0.9281612562990742,
268
+ "grad_norm": 78.69176483154297,
269
+ "learning_rate": 4.582726831635129e-05,
270
+ "loss": 24.69483642578125,
271
+ "step": 495
272
+ },
273
+ {
274
+ "epoch": 0.9562873549748037,
275
+ "grad_norm": 71.7799072265625,
276
+ "learning_rate": 4.564531780688986e-05,
277
+ "loss": 23.468556722005207,
278
+ "step": 510
279
+ },
280
+ {
281
+ "epoch": 0.9844134536505332,
282
+ "grad_norm": 99.54678344726562,
283
+ "learning_rate": 4.5463367297428435e-05,
284
+ "loss": 24.51992390950521,
285
+ "step": 525
286
+ },
287
+ {
288
+ "epoch": 1.011250439470292,
289
+ "grad_norm": 81.2381362915039,
290
+ "learning_rate": 4.528141678796701e-05,
291
+ "loss": 22.73736572265625,
292
+ "step": 540
293
+ },
294
+ {
295
+ "epoch": 1.0393765381460214,
296
+ "grad_norm": 72.6605224609375,
297
+ "learning_rate": 4.509946627850558e-05,
298
+ "loss": 24.33416748046875,
299
+ "step": 555
300
+ },
301
+ {
302
+ "epoch": 1.0675026368217508,
303
+ "grad_norm": 80.05354309082031,
304
+ "learning_rate": 4.4917515769044156e-05,
305
+ "loss": 22.052213541666667,
306
+ "step": 570
307
+ },
308
+ {
309
+ "epoch": 1.0956287354974803,
310
+ "grad_norm": 90.22277069091797,
311
+ "learning_rate": 4.473556525958273e-05,
312
+ "loss": 22.770609537760418,
313
+ "step": 585
314
+ },
315
+ {
316
+ "epoch": 1.12375483417321,
317
+ "grad_norm": 69.45885467529297,
318
+ "learning_rate": 4.4553614750121304e-05,
319
+ "loss": 24.028635660807293,
320
+ "step": 600
321
+ },
322
+ {
323
+ "epoch": 1.12375483417321,
324
+ "eval_accuracy": 0.6608695652173913,
325
+ "eval_loss": 1.49661386013031,
326
+ "eval_macro_f1": 0.6466193853427896,
327
+ "eval_runtime": 2.2405,
328
+ "eval_samples_per_second": 153.984,
329
+ "eval_steps_per_second": 19.639,
330
+ "step": 600
331
+ },
332
+ {
333
+ "epoch": 1.1518809328489394,
334
+ "grad_norm": 109.61043548583984,
335
+ "learning_rate": 4.437166424065988e-05,
336
+ "loss": 23.77248331705729,
337
+ "step": 615
338
+ },
339
+ {
340
+ "epoch": 1.180007031524669,
341
+ "grad_norm": 71.86944580078125,
342
+ "learning_rate": 4.418971373119845e-05,
343
+ "loss": 22.4523193359375,
344
+ "step": 630
345
+ },
346
+ {
347
+ "epoch": 1.2081331302003984,
348
+ "grad_norm": 79.43173217773438,
349
+ "learning_rate": 4.4007763221737025e-05,
350
+ "loss": 23.30051472981771,
351
+ "step": 645
352
+ },
353
+ {
354
+ "epoch": 1.236259228876128,
355
+ "grad_norm": 73.39543914794922,
356
+ "learning_rate": 4.38258127122756e-05,
357
+ "loss": 23.162101236979165,
358
+ "step": 660
359
+ },
360
+ {
361
+ "epoch": 1.2643853275518575,
362
+ "grad_norm": 92.3052978515625,
363
+ "learning_rate": 4.3643862202814165e-05,
364
+ "loss": 22.967840576171874,
365
+ "step": 675
366
+ },
367
+ {
368
+ "epoch": 1.292511426227587,
369
+ "grad_norm": 79.57266998291016,
370
+ "learning_rate": 4.346191169335274e-05,
371
+ "loss": 24.993180338541666,
372
+ "step": 690
373
+ },
374
+ {
375
+ "epoch": 1.3206375249033164,
376
+ "grad_norm": 81.71668243408203,
377
+ "learning_rate": 4.327996118389131e-05,
378
+ "loss": 23.013671875,
379
+ "step": 705
380
+ },
381
+ {
382
+ "epoch": 1.3487636235790461,
383
+ "grad_norm": 64.0071029663086,
384
+ "learning_rate": 4.3098010674429886e-05,
385
+ "loss": 23.570048014322918,
386
+ "step": 720
387
+ },
388
+ {
389
+ "epoch": 1.3768897222547756,
390
+ "grad_norm": 98.42646789550781,
391
+ "learning_rate": 4.291606016496847e-05,
392
+ "loss": 22.822066243489584,
393
+ "step": 735
394
+ },
395
+ {
396
+ "epoch": 1.405015820930505,
397
+ "grad_norm": 77.34905242919922,
398
+ "learning_rate": 4.273410965550704e-05,
399
+ "loss": 24.35296630859375,
400
+ "step": 750
401
+ },
402
+ {
403
+ "epoch": 1.405015820930505,
404
+ "eval_accuracy": 0.6608695652173913,
405
+ "eval_loss": 1.4775240421295166,
406
+ "eval_macro_f1": 0.6485427050773,
407
+ "eval_runtime": 2.2991,
408
+ "eval_samples_per_second": 150.061,
409
+ "eval_steps_per_second": 19.138,
410
+ "step": 750
411
+ },
412
+ {
413
+ "epoch": 1.4331419196062347,
414
+ "grad_norm": 74.36935424804688,
415
+ "learning_rate": 4.2552159146045614e-05,
416
+ "loss": 24.365966796875,
417
+ "step": 765
418
+ },
419
+ {
420
+ "epoch": 1.4612680182819642,
421
+ "grad_norm": 72.57489013671875,
422
+ "learning_rate": 4.237020863658419e-05,
423
+ "loss": 22.283140055338542,
424
+ "step": 780
425
+ },
426
+ {
427
+ "epoch": 1.4893941169576936,
428
+ "grad_norm": 66.50872039794922,
429
+ "learning_rate": 4.218825812712276e-05,
430
+ "loss": 22.849454752604167,
431
+ "step": 795
432
+ },
433
+ {
434
+ "epoch": 1.5175202156334233,
435
+ "grad_norm": 73.18653869628906,
436
+ "learning_rate": 4.2006307617661335e-05,
437
+ "loss": 23.213165283203125,
438
+ "step": 810
439
+ },
440
+ {
441
+ "epoch": 1.5456463143091526,
442
+ "grad_norm": 100.36980438232422,
443
+ "learning_rate": 4.182435710819991e-05,
444
+ "loss": 22.919950358072917,
445
+ "step": 825
446
+ },
447
+ {
448
+ "epoch": 1.5737724129848822,
449
+ "grad_norm": 92.35721588134766,
450
+ "learning_rate": 4.1642406598738476e-05,
451
+ "loss": 23.443257649739582,
452
+ "step": 840
453
+ },
454
+ {
455
+ "epoch": 1.6018985116606117,
456
+ "grad_norm": 79.11441802978516,
457
+ "learning_rate": 4.146045608927705e-05,
458
+ "loss": 23.26278076171875,
459
+ "step": 855
460
+ },
461
+ {
462
+ "epoch": 1.6300246103363412,
463
+ "grad_norm": 92.07249450683594,
464
+ "learning_rate": 4.127850557981562e-05,
465
+ "loss": 21.62847900390625,
466
+ "step": 870
467
+ },
468
+ {
469
+ "epoch": 1.6581507090120708,
470
+ "grad_norm": 62.01802444458008,
471
+ "learning_rate": 4.1096555070354197e-05,
472
+ "loss": 22.551171875,
473
+ "step": 885
474
+ },
475
+ {
476
+ "epoch": 1.6862768076878003,
477
+ "grad_norm": 87.6247787475586,
478
+ "learning_rate": 4.091460456089277e-05,
479
+ "loss": 23.632059733072918,
480
+ "step": 900
481
+ },
482
+ {
483
+ "epoch": 1.6862768076878003,
484
+ "eval_accuracy": 0.6898550724637681,
485
+ "eval_loss": 1.4343311786651611,
486
+ "eval_macro_f1": 0.6784067065231657,
487
+ "eval_runtime": 2.2935,
488
+ "eval_samples_per_second": 150.428,
489
+ "eval_steps_per_second": 19.185,
490
+ "step": 900
491
+ },
492
+ {
493
+ "epoch": 1.7144029063635298,
494
+ "grad_norm": 77.10883331298828,
495
+ "learning_rate": 4.0732654051431344e-05,
496
+ "loss": 23.429276529947916,
497
+ "step": 915
498
+ },
499
+ {
500
+ "epoch": 1.7425290050392594,
501
+ "grad_norm": 88.47496795654297,
502
+ "learning_rate": 4.055070354196992e-05,
503
+ "loss": 23.187703450520832,
504
+ "step": 930
505
+ },
506
+ {
507
+ "epoch": 1.770655103714989,
508
+ "grad_norm": 104.27533721923828,
509
+ "learning_rate": 4.036875303250849e-05,
510
+ "loss": 24.269075520833333,
511
+ "step": 945
512
+ },
513
+ {
514
+ "epoch": 1.7987812023907184,
515
+ "grad_norm": 67.3711166381836,
516
+ "learning_rate": 4.0186802523047065e-05,
517
+ "loss": 22.98969930013021,
518
+ "step": 960
519
+ },
520
+ {
521
+ "epoch": 1.826907301066448,
522
+ "grad_norm": 67.43853759765625,
523
+ "learning_rate": 4.0004852013585645e-05,
524
+ "loss": 23.56575724283854,
525
+ "step": 975
526
+ },
527
+ {
528
+ "epoch": 1.8550333997421773,
529
+ "grad_norm": 77.04778289794922,
530
+ "learning_rate": 3.982290150412422e-05,
531
+ "loss": 22.3833251953125,
532
+ "step": 990
533
+ },
534
+ {
535
+ "epoch": 1.883159498417907,
536
+ "grad_norm": 83.1104507446289,
537
+ "learning_rate": 3.9640950994662786e-05,
538
+ "loss": 22.058768717447915,
539
+ "step": 1005
540
+ },
541
+ {
542
+ "epoch": 1.9112855970936364,
543
+ "grad_norm": 67.31427001953125,
544
+ "learning_rate": 3.945900048520136e-05,
545
+ "loss": 23.626953125,
546
+ "step": 1020
547
+ },
548
+ {
549
+ "epoch": 1.939411695769366,
550
+ "grad_norm": 78.14697265625,
551
+ "learning_rate": 3.927704997573993e-05,
552
+ "loss": 23.199896240234374,
553
+ "step": 1035
554
+ },
555
+ {
556
+ "epoch": 1.9675377944450956,
557
+ "grad_norm": 86.21821594238281,
558
+ "learning_rate": 3.909509946627851e-05,
559
+ "loss": 22.229060872395834,
560
+ "step": 1050
561
+ },
562
+ {
563
+ "epoch": 1.9675377944450956,
564
+ "eval_accuracy": 0.6840579710144927,
565
+ "eval_loss": 1.3762412071228027,
566
+ "eval_macro_f1": 0.6729193842335214,
567
+ "eval_runtime": 2.2854,
568
+ "eval_samples_per_second": 150.959,
569
+ "eval_steps_per_second": 19.253,
570
+ "step": 1050
571
+ },
572
+ {
573
+ "epoch": 1.995663893120825,
574
+ "grad_norm": 109.04509735107422,
575
+ "learning_rate": 3.891314895681708e-05,
576
+ "loss": 22.08022664388021,
577
+ "step": 1065
578
+ },
579
+ {
580
+ "epoch": 2.022500878940584,
581
+ "grad_norm": 63.62330627441406,
582
+ "learning_rate": 3.8731198447355654e-05,
583
+ "loss": 19.795827229817707,
584
+ "step": 1080
585
+ },
586
+ {
587
+ "epoch": 2.050626977616313,
588
+ "grad_norm": 92.98448181152344,
589
+ "learning_rate": 3.854924793789423e-05,
590
+ "loss": 21.829217529296876,
591
+ "step": 1095
592
+ },
593
+ {
594
+ "epoch": 2.0787530762920428,
595
+ "grad_norm": 108.95834350585938,
596
+ "learning_rate": 3.83672974284328e-05,
597
+ "loss": 21.407171630859374,
598
+ "step": 1110
599
+ },
600
+ {
601
+ "epoch": 2.106879174967772,
602
+ "grad_norm": 86.67636108398438,
603
+ "learning_rate": 3.8185346918971375e-05,
604
+ "loss": 22.318717447916665,
605
+ "step": 1125
606
+ },
607
+ {
608
+ "epoch": 2.1350052736435017,
609
+ "grad_norm": 90.65144348144531,
610
+ "learning_rate": 3.800339640950995e-05,
611
+ "loss": 22.579439290364583,
612
+ "step": 1140
613
+ },
614
+ {
615
+ "epoch": 2.1631313723192314,
616
+ "grad_norm": 160.0935516357422,
617
+ "learning_rate": 3.782144590004852e-05,
618
+ "loss": 21.32430419921875,
619
+ "step": 1155
620
+ },
621
+ {
622
+ "epoch": 2.1912574709949606,
623
+ "grad_norm": 80.67872619628906,
624
+ "learning_rate": 3.7639495390587096e-05,
625
+ "loss": 22.795635986328126,
626
+ "step": 1170
627
+ },
628
+ {
629
+ "epoch": 2.2193835696706903,
630
+ "grad_norm": 78.44005584716797,
631
+ "learning_rate": 3.745754488112567e-05,
632
+ "loss": 21.308553059895832,
633
+ "step": 1185
634
+ },
635
+ {
636
+ "epoch": 2.24750966834642,
637
+ "grad_norm": 95.2944107055664,
638
+ "learning_rate": 3.7275594371664243e-05,
639
+ "loss": 20.899271647135418,
640
+ "step": 1200
641
+ },
642
+ {
643
+ "epoch": 2.24750966834642,
644
+ "eval_accuracy": 0.6985507246376812,
645
+ "eval_loss": 1.3909375667572021,
646
+ "eval_macro_f1": 0.6854383677464303,
647
+ "eval_runtime": 2.3405,
648
+ "eval_samples_per_second": 147.407,
649
+ "eval_steps_per_second": 18.8,
650
+ "step": 1200
651
+ },
652
+ {
653
+ "epoch": 2.275635767022149,
654
+ "grad_norm": 83.903076171875,
655
+ "learning_rate": 3.709364386220282e-05,
656
+ "loss": 23.106620279947915,
657
+ "step": 1215
658
+ },
659
+ {
660
+ "epoch": 2.303761865697879,
661
+ "grad_norm": 89.56684875488281,
662
+ "learning_rate": 3.691169335274139e-05,
663
+ "loss": 20.57239990234375,
664
+ "step": 1230
665
+ },
666
+ {
667
+ "epoch": 2.3318879643736086,
668
+ "grad_norm": 99.3587417602539,
669
+ "learning_rate": 3.6729742843279964e-05,
670
+ "loss": 21.402762858072915,
671
+ "step": 1245
672
+ },
673
+ {
674
+ "epoch": 2.360014063049338,
675
+ "grad_norm": 95.15524291992188,
676
+ "learning_rate": 3.654779233381854e-05,
677
+ "loss": 20.991483561197917,
678
+ "step": 1260
679
+ },
680
+ {
681
+ "epoch": 2.3881401617250675,
682
+ "grad_norm": 87.97482299804688,
683
+ "learning_rate": 3.636584182435711e-05,
684
+ "loss": 22.1961669921875,
685
+ "step": 1275
686
+ },
687
+ {
688
+ "epoch": 2.4162662604007967,
689
+ "grad_norm": 105.3332290649414,
690
+ "learning_rate": 3.6183891314895685e-05,
691
+ "loss": 21.362872314453124,
692
+ "step": 1290
693
+ },
694
+ {
695
+ "epoch": 2.4443923590765264,
696
+ "grad_norm": 67.10509490966797,
697
+ "learning_rate": 3.600194080543426e-05,
698
+ "loss": 21.770963541666667,
699
+ "step": 1305
700
+ },
701
+ {
702
+ "epoch": 2.472518457752256,
703
+ "grad_norm": 93.77086639404297,
704
+ "learning_rate": 3.581999029597283e-05,
705
+ "loss": 22.990873209635417,
706
+ "step": 1320
707
+ },
708
+ {
709
+ "epoch": 2.5006445564279853,
710
+ "grad_norm": 67.30560302734375,
711
+ "learning_rate": 3.56380397865114e-05,
712
+ "loss": 21.035380045572918,
713
+ "step": 1335
714
+ },
715
+ {
716
+ "epoch": 2.528770655103715,
717
+ "grad_norm": 127.03382873535156,
718
+ "learning_rate": 3.545608927704997e-05,
719
+ "loss": 21.682499186197916,
720
+ "step": 1350
721
+ },
722
+ {
723
+ "epoch": 2.528770655103715,
724
+ "eval_accuracy": 0.6811594202898551,
725
+ "eval_loss": 1.4433109760284424,
726
+ "eval_macro_f1": 0.6794718548394098,
727
+ "eval_runtime": 2.2369,
728
+ "eval_samples_per_second": 154.234,
729
+ "eval_steps_per_second": 19.67,
730
+ "step": 1350
731
+ },
732
+ {
733
+ "epoch": 2.5568967537794443,
734
+ "grad_norm": 92.79231262207031,
735
+ "learning_rate": 3.527413876758855e-05,
736
+ "loss": 21.885359700520834,
737
+ "step": 1365
738
+ },
739
+ {
740
+ "epoch": 2.585022852455174,
741
+ "grad_norm": 111.23881530761719,
742
+ "learning_rate": 3.509218825812712e-05,
743
+ "loss": 20.30838623046875,
744
+ "step": 1380
745
+ },
746
+ {
747
+ "epoch": 2.6131489511309036,
748
+ "grad_norm": 72.55780029296875,
749
+ "learning_rate": 3.4910237748665694e-05,
750
+ "loss": 18.903086344401043,
751
+ "step": 1395
752
+ },
753
+ {
754
+ "epoch": 2.641275049806633,
755
+ "grad_norm": 73.78776550292969,
756
+ "learning_rate": 3.472828723920427e-05,
757
+ "loss": 22.561869303385418,
758
+ "step": 1410
759
+ },
760
+ {
761
+ "epoch": 2.6694011484823625,
762
+ "grad_norm": 86.27180480957031,
763
+ "learning_rate": 3.454633672974285e-05,
764
+ "loss": 21.844730631510416,
765
+ "step": 1425
766
+ },
767
+ {
768
+ "epoch": 2.6975272471580922,
769
+ "grad_norm": 65.71673583984375,
770
+ "learning_rate": 3.436438622028142e-05,
771
+ "loss": 21.621647135416666,
772
+ "step": 1440
773
+ },
774
+ {
775
+ "epoch": 2.7256533458338215,
776
+ "grad_norm": 94.1865463256836,
777
+ "learning_rate": 3.4182435710819996e-05,
778
+ "loss": 21.298856608072917,
779
+ "step": 1455
780
+ },
781
+ {
782
+ "epoch": 2.753779444509551,
783
+ "grad_norm": 82.48493957519531,
784
+ "learning_rate": 3.400048520135857e-05,
785
+ "loss": 21.100826009114584,
786
+ "step": 1470
787
+ },
788
+ {
789
+ "epoch": 2.781905543185281,
790
+ "grad_norm": 96.52738952636719,
791
+ "learning_rate": 3.381853469189714e-05,
792
+ "loss": 22.47982177734375,
793
+ "step": 1485
794
+ },
795
+ {
796
+ "epoch": 2.81003164186101,
797
+ "grad_norm": 87.80317687988281,
798
+ "learning_rate": 3.363658418243571e-05,
799
+ "loss": 21.95230916341146,
800
+ "step": 1500
801
+ },
802
+ {
803
+ "epoch": 2.81003164186101,
804
+ "eval_accuracy": 0.6869565217391305,
805
+ "eval_loss": 1.3259601593017578,
806
+ "eval_macro_f1": 0.6715942315942316,
807
+ "eval_runtime": 2.2965,
808
+ "eval_samples_per_second": 150.226,
809
+ "eval_steps_per_second": 19.159,
810
+ "step": 1500
811
+ },
812
+ {
813
+ "epoch": 2.8381577405367397,
814
+ "grad_norm": 134.34188842773438,
815
+ "learning_rate": 3.3454633672974284e-05,
816
+ "loss": 22.170475260416666,
817
+ "step": 1515
818
+ },
819
+ {
820
+ "epoch": 2.8662838392124694,
821
+ "grad_norm": 72.98772430419922,
822
+ "learning_rate": 3.327268316351286e-05,
823
+ "loss": 23.180810546875,
824
+ "step": 1530
825
+ },
826
+ {
827
+ "epoch": 2.8944099378881987,
828
+ "grad_norm": 131.15469360351562,
829
+ "learning_rate": 3.309073265405143e-05,
830
+ "loss": 21.58048095703125,
831
+ "step": 1545
832
+ },
833
+ {
834
+ "epoch": 2.9225360365639284,
835
+ "grad_norm": 75.53298950195312,
836
+ "learning_rate": 3.2908782144590005e-05,
837
+ "loss": 20.257352701822917,
838
+ "step": 1560
839
+ },
840
+ {
841
+ "epoch": 2.950662135239658,
842
+ "grad_norm": 100.07022094726562,
843
+ "learning_rate": 3.272683163512858e-05,
844
+ "loss": 19.97838134765625,
845
+ "step": 1575
846
+ },
847
+ {
848
+ "epoch": 2.9787882339153873,
849
+ "grad_norm": 78.29119110107422,
850
+ "learning_rate": 3.254488112566715e-05,
851
+ "loss": 20.777811686197918,
852
+ "step": 1590
853
+ },
854
+ {
855
+ "epoch": 3.005625219735146,
856
+ "grad_norm": 92.47520446777344,
857
+ "learning_rate": 3.2362930616205726e-05,
858
+ "loss": 22.04563191731771,
859
+ "step": 1605
860
+ },
861
+ {
862
+ "epoch": 3.0337513184108755,
863
+ "grad_norm": 77.91747283935547,
864
+ "learning_rate": 3.21809801067443e-05,
865
+ "loss": 20.988616943359375,
866
+ "step": 1620
867
+ },
868
+ {
869
+ "epoch": 3.0618774170866048,
870
+ "grad_norm": 80.09091186523438,
871
+ "learning_rate": 3.199902959728287e-05,
872
+ "loss": 20.8621826171875,
873
+ "step": 1635
874
+ },
875
+ {
876
+ "epoch": 3.0900035157623345,
877
+ "grad_norm": 94.06583404541016,
878
+ "learning_rate": 3.1817079087821447e-05,
879
+ "loss": 21.464599609375,
880
+ "step": 1650
881
+ },
882
+ {
883
+ "epoch": 3.0900035157623345,
884
+ "eval_accuracy": 0.7014492753623188,
885
+ "eval_loss": 1.3364124298095703,
886
+ "eval_macro_f1": 0.6895917207672184,
887
+ "eval_runtime": 2.2934,
888
+ "eval_samples_per_second": 150.431,
889
+ "eval_steps_per_second": 19.185,
890
+ "step": 1650
891
+ }
892
+ ],
893
+ "logging_steps": 15,
894
+ "max_steps": 4272,
895
+ "num_input_tokens_seen": 0,
896
+ "num_train_epochs": 8,
897
+ "save_steps": 150,
898
+ "stateful_callbacks": {
899
+ "TrainerControl": {
900
+ "args": {
901
+ "should_epoch_stop": false,
902
+ "should_evaluate": false,
903
+ "should_log": false,
904
+ "should_save": true,
905
+ "should_training_stop": false
906
+ },
907
+ "attributes": {}
908
+ }
909
+ },
910
+ "total_flos": 3882788279287808.0,
911
+ "train_batch_size": 2,
912
+ "trial_name": null,
913
+ "trial_params": null
914
+ }
sft/checkpoint-1650/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37d5b6b59a9b3ebbb703393ea1b80963b65b36ea5e43b5614682c24b6cd469ff
3
+ size 5201