Add files using upload-large-folder tool
Browse files- notebooks/results/checkpoint-1000/model.safetensors +3 -0
- notebooks/results/checkpoint-1000/optimizer.pt +3 -0
- notebooks/results/checkpoint-1000/rng_state.pth +3 -0
- notebooks/results/checkpoint-1000/scheduler.pt +3 -0
- notebooks/results/checkpoint-1000/training_args.bin +3 -0
- notebooks/results/checkpoint-1500/model.safetensors +3 -0
- notebooks/results/checkpoint-1500/rng_state.pth +3 -0
- notebooks/results/checkpoint-1500/scheduler.pt +3 -0
- notebooks/results/checkpoint-1500/trainer_state.json +139 -0
- notebooks/results/checkpoint-1500/training_args.bin +3 -0
- notebooks/results/checkpoint-2000/config.json +26 -0
- notebooks/results/checkpoint-2000/trainer_state.json +174 -0
- notebooks/results/checkpoint-2500/config.json +26 -0
- notebooks/results/checkpoint-2500/trainer_state.json +209 -0
- notebooks/sentiment-bert-model/model.safetensors +3 -0
- notebooks/sentiment-bert-model/training_args.bin +3 -0
- sentiment-bert-model/optimizer.pt +3 -0
- sentiment-bert-model/rng_state.pth +3 -0
- sentiment-bert-model/scheduler.pt +3 -0
- sentiment-bert-model/training_args.bin +3 -0
notebooks/results/checkpoint-1000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc4191a359ddca9d26e90585df2bc8e8313cddc802656c8a134e96a5d914d44f
|
| 3 |
+
size 437958648
|
notebooks/results/checkpoint-1000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4050e7abc313264e3bcc613c44bfbb634ba5a01b4b864e8e1ce7e17a2b40975d
|
| 3 |
+
size 876033163
|
notebooks/results/checkpoint-1000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7cb7c56bb5d97cf8a37e1e9232a07c9213d01707fba8abeb3ea65a0572ea87c8
|
| 3 |
+
size 14455
|
notebooks/results/checkpoint-1000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf9faf68418b27d6f4ba8595dfa349b66d99645e970f3d5eb396d0ac3ef44d61
|
| 3 |
+
size 1465
|
notebooks/results/checkpoint-1000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b158a7fd39c76db160cbdea68fa9ea7ba8a3a1d5a835ed6d7fc5813cda06fee
|
| 3 |
+
size 5649
|
notebooks/results/checkpoint-1500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7cdef91088766efb75a6bc2bce8622408b5709252e411887b6006dd91f4bc952
|
| 3 |
+
size 437958648
|
notebooks/results/checkpoint-1500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6281a786764e7c16d52e1aa9a084d82b3e249f5239c25ef82dea6c5a00338d6
|
| 3 |
+
size 14455
|
notebooks/results/checkpoint-1500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:009d67580683899a853b9d8c7780d10e3c03d6bda94e005ae5e058f4587570ca
|
| 3 |
+
size 1465
|
notebooks/results/checkpoint-1500/trainer_state.json
ADDED
|
@@ -0,0 +1,139 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.9596928982725528,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 1500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.06397952655150352,
|
| 14 |
+
"grad_norm": 5.188015460968018,
|
| 15 |
+
"learning_rate": 4.8944337811900195e-05,
|
| 16 |
+
"loss": 0.5162,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.12795905310300704,
|
| 21 |
+
"grad_norm": 8.62886905670166,
|
| 22 |
+
"learning_rate": 4.7878012369375135e-05,
|
| 23 |
+
"loss": 0.4123,
|
| 24 |
+
"step": 200
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.19193857965451055,
|
| 28 |
+
"grad_norm": 6.661285877227783,
|
| 29 |
+
"learning_rate": 4.681168692685008e-05,
|
| 30 |
+
"loss": 0.4106,
|
| 31 |
+
"step": 300
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.2559181062060141,
|
| 35 |
+
"grad_norm": 7.992310523986816,
|
| 36 |
+
"learning_rate": 4.5745361484325014e-05,
|
| 37 |
+
"loss": 0.3619,
|
| 38 |
+
"step": 400
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.3198976327575176,
|
| 42 |
+
"grad_norm": 8.48903751373291,
|
| 43 |
+
"learning_rate": 4.467903604179996e-05,
|
| 44 |
+
"loss": 0.3724,
|
| 45 |
+
"step": 500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.3838771593090211,
|
| 49 |
+
"grad_norm": 7.3620219230651855,
|
| 50 |
+
"learning_rate": 4.3612710599274906e-05,
|
| 51 |
+
"loss": 0.3582,
|
| 52 |
+
"step": 600
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.44785668586052463,
|
| 56 |
+
"grad_norm": 7.127757549285889,
|
| 57 |
+
"learning_rate": 4.254638515674984e-05,
|
| 58 |
+
"loss": 0.351,
|
| 59 |
+
"step": 700
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.5118362124120281,
|
| 63 |
+
"grad_norm": 8.284778594970703,
|
| 64 |
+
"learning_rate": 4.1480059714224785e-05,
|
| 65 |
+
"loss": 0.3517,
|
| 66 |
+
"step": 800
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.5758157389635317,
|
| 70 |
+
"grad_norm": 6.389641284942627,
|
| 71 |
+
"learning_rate": 4.0413734271699725e-05,
|
| 72 |
+
"loss": 0.3197,
|
| 73 |
+
"step": 900
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.6397952655150352,
|
| 77 |
+
"grad_norm": 8.652924537658691,
|
| 78 |
+
"learning_rate": 3.9347408829174664e-05,
|
| 79 |
+
"loss": 0.3457,
|
| 80 |
+
"step": 1000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.7037747920665387,
|
| 84 |
+
"grad_norm": 9.87730598449707,
|
| 85 |
+
"learning_rate": 3.828108338664961e-05,
|
| 86 |
+
"loss": 0.3152,
|
| 87 |
+
"step": 1100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.7677543186180422,
|
| 91 |
+
"grad_norm": 9.235931396484375,
|
| 92 |
+
"learning_rate": 3.721475794412455e-05,
|
| 93 |
+
"loss": 0.3312,
|
| 94 |
+
"step": 1200
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.8317338451695457,
|
| 98 |
+
"grad_norm": 8.75272274017334,
|
| 99 |
+
"learning_rate": 3.614843250159949e-05,
|
| 100 |
+
"loss": 0.3098,
|
| 101 |
+
"step": 1300
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.8957133717210493,
|
| 105 |
+
"grad_norm": 3.6930184364318848,
|
| 106 |
+
"learning_rate": 3.508210705907443e-05,
|
| 107 |
+
"loss": 0.3057,
|
| 108 |
+
"step": 1400
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.9596928982725528,
|
| 112 |
+
"grad_norm": 15.71256160736084,
|
| 113 |
+
"learning_rate": 3.4015781616549375e-05,
|
| 114 |
+
"loss": 0.2994,
|
| 115 |
+
"step": 1500
|
| 116 |
+
}
|
| 117 |
+
],
|
| 118 |
+
"logging_steps": 100,
|
| 119 |
+
"max_steps": 4689,
|
| 120 |
+
"num_input_tokens_seen": 0,
|
| 121 |
+
"num_train_epochs": 3,
|
| 122 |
+
"save_steps": 500,
|
| 123 |
+
"stateful_callbacks": {
|
| 124 |
+
"TrainerControl": {
|
| 125 |
+
"args": {
|
| 126 |
+
"should_epoch_stop": false,
|
| 127 |
+
"should_evaluate": false,
|
| 128 |
+
"should_log": false,
|
| 129 |
+
"should_save": true,
|
| 130 |
+
"should_training_stop": false
|
| 131 |
+
},
|
| 132 |
+
"attributes": {}
|
| 133 |
+
}
|
| 134 |
+
},
|
| 135 |
+
"total_flos": 1578666332160000.0,
|
| 136 |
+
"train_batch_size": 16,
|
| 137 |
+
"trial_name": null,
|
| 138 |
+
"trial_params": null
|
| 139 |
+
}
|
notebooks/results/checkpoint-1500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b158a7fd39c76db160cbdea68fa9ea7ba8a3a1d5a835ed6d7fc5813cda06fee
|
| 3 |
+
size 5649
|
notebooks/results/checkpoint-2000/config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"gradient_checkpointing": false,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 3072,
|
| 13 |
+
"layer_norm_eps": 1e-12,
|
| 14 |
+
"max_position_embeddings": 512,
|
| 15 |
+
"model_type": "bert",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 12,
|
| 18 |
+
"pad_token_id": 0,
|
| 19 |
+
"position_embedding_type": "absolute",
|
| 20 |
+
"problem_type": "single_label_classification",
|
| 21 |
+
"torch_dtype": "float32",
|
| 22 |
+
"transformers_version": "4.51.3",
|
| 23 |
+
"type_vocab_size": 2,
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"vocab_size": 30522
|
| 26 |
+
}
|
notebooks/results/checkpoint-2000/trainer_state.json
ADDED
|
@@ -0,0 +1,174 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.2795905310300704,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.06397952655150352,
|
| 14 |
+
"grad_norm": 5.188015460968018,
|
| 15 |
+
"learning_rate": 4.8944337811900195e-05,
|
| 16 |
+
"loss": 0.5162,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.12795905310300704,
|
| 21 |
+
"grad_norm": 8.62886905670166,
|
| 22 |
+
"learning_rate": 4.7878012369375135e-05,
|
| 23 |
+
"loss": 0.4123,
|
| 24 |
+
"step": 200
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.19193857965451055,
|
| 28 |
+
"grad_norm": 6.661285877227783,
|
| 29 |
+
"learning_rate": 4.681168692685008e-05,
|
| 30 |
+
"loss": 0.4106,
|
| 31 |
+
"step": 300
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.2559181062060141,
|
| 35 |
+
"grad_norm": 7.992310523986816,
|
| 36 |
+
"learning_rate": 4.5745361484325014e-05,
|
| 37 |
+
"loss": 0.3619,
|
| 38 |
+
"step": 400
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.3198976327575176,
|
| 42 |
+
"grad_norm": 8.48903751373291,
|
| 43 |
+
"learning_rate": 4.467903604179996e-05,
|
| 44 |
+
"loss": 0.3724,
|
| 45 |
+
"step": 500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.3838771593090211,
|
| 49 |
+
"grad_norm": 7.3620219230651855,
|
| 50 |
+
"learning_rate": 4.3612710599274906e-05,
|
| 51 |
+
"loss": 0.3582,
|
| 52 |
+
"step": 600
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.44785668586052463,
|
| 56 |
+
"grad_norm": 7.127757549285889,
|
| 57 |
+
"learning_rate": 4.254638515674984e-05,
|
| 58 |
+
"loss": 0.351,
|
| 59 |
+
"step": 700
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.5118362124120281,
|
| 63 |
+
"grad_norm": 8.284778594970703,
|
| 64 |
+
"learning_rate": 4.1480059714224785e-05,
|
| 65 |
+
"loss": 0.3517,
|
| 66 |
+
"step": 800
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.5758157389635317,
|
| 70 |
+
"grad_norm": 6.389641284942627,
|
| 71 |
+
"learning_rate": 4.0413734271699725e-05,
|
| 72 |
+
"loss": 0.3197,
|
| 73 |
+
"step": 900
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.6397952655150352,
|
| 77 |
+
"grad_norm": 8.652924537658691,
|
| 78 |
+
"learning_rate": 3.9347408829174664e-05,
|
| 79 |
+
"loss": 0.3457,
|
| 80 |
+
"step": 1000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.7037747920665387,
|
| 84 |
+
"grad_norm": 9.87730598449707,
|
| 85 |
+
"learning_rate": 3.828108338664961e-05,
|
| 86 |
+
"loss": 0.3152,
|
| 87 |
+
"step": 1100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.7677543186180422,
|
| 91 |
+
"grad_norm": 9.235931396484375,
|
| 92 |
+
"learning_rate": 3.721475794412455e-05,
|
| 93 |
+
"loss": 0.3312,
|
| 94 |
+
"step": 1200
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.8317338451695457,
|
| 98 |
+
"grad_norm": 8.75272274017334,
|
| 99 |
+
"learning_rate": 3.614843250159949e-05,
|
| 100 |
+
"loss": 0.3098,
|
| 101 |
+
"step": 1300
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.8957133717210493,
|
| 105 |
+
"grad_norm": 3.6930184364318848,
|
| 106 |
+
"learning_rate": 3.508210705907443e-05,
|
| 107 |
+
"loss": 0.3057,
|
| 108 |
+
"step": 1400
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.9596928982725528,
|
| 112 |
+
"grad_norm": 15.71256160736084,
|
| 113 |
+
"learning_rate": 3.4015781616549375e-05,
|
| 114 |
+
"loss": 0.2994,
|
| 115 |
+
"step": 1500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 1.0236724248240563,
|
| 119 |
+
"grad_norm": 10.11008071899414,
|
| 120 |
+
"learning_rate": 3.2949456174024315e-05,
|
| 121 |
+
"loss": 0.2945,
|
| 122 |
+
"step": 1600
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.0876519513755598,
|
| 126 |
+
"grad_norm": 1.052371859550476,
|
| 127 |
+
"learning_rate": 3.1883130731499254e-05,
|
| 128 |
+
"loss": 0.2072,
|
| 129 |
+
"step": 1700
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.1516314779270633,
|
| 133 |
+
"grad_norm": 0.17214666306972504,
|
| 134 |
+
"learning_rate": 3.08168052889742e-05,
|
| 135 |
+
"loss": 0.1915,
|
| 136 |
+
"step": 1800
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 1.2156110044785668,
|
| 140 |
+
"grad_norm": 3.5573925971984863,
|
| 141 |
+
"learning_rate": 2.9750479846449137e-05,
|
| 142 |
+
"loss": 0.2268,
|
| 143 |
+
"step": 1900
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.2795905310300704,
|
| 147 |
+
"grad_norm": 12.984672546386719,
|
| 148 |
+
"learning_rate": 2.868415440392408e-05,
|
| 149 |
+
"loss": 0.1639,
|
| 150 |
+
"step": 2000
|
| 151 |
+
}
|
| 152 |
+
],
|
| 153 |
+
"logging_steps": 100,
|
| 154 |
+
"max_steps": 4689,
|
| 155 |
+
"num_input_tokens_seen": 0,
|
| 156 |
+
"num_train_epochs": 3,
|
| 157 |
+
"save_steps": 500,
|
| 158 |
+
"stateful_callbacks": {
|
| 159 |
+
"TrainerControl": {
|
| 160 |
+
"args": {
|
| 161 |
+
"should_epoch_stop": false,
|
| 162 |
+
"should_evaluate": false,
|
| 163 |
+
"should_log": false,
|
| 164 |
+
"should_save": true,
|
| 165 |
+
"should_training_stop": false
|
| 166 |
+
},
|
| 167 |
+
"attributes": {}
|
| 168 |
+
}
|
| 169 |
+
},
|
| 170 |
+
"total_flos": 2104362220769280.0,
|
| 171 |
+
"train_batch_size": 16,
|
| 172 |
+
"trial_name": null,
|
| 173 |
+
"trial_params": null
|
| 174 |
+
}
|
notebooks/results/checkpoint-2500/config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"gradient_checkpointing": false,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 3072,
|
| 13 |
+
"layer_norm_eps": 1e-12,
|
| 14 |
+
"max_position_embeddings": 512,
|
| 15 |
+
"model_type": "bert",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 12,
|
| 18 |
+
"pad_token_id": 0,
|
| 19 |
+
"position_embedding_type": "absolute",
|
| 20 |
+
"problem_type": "single_label_classification",
|
| 21 |
+
"torch_dtype": "float32",
|
| 22 |
+
"transformers_version": "4.51.3",
|
| 23 |
+
"type_vocab_size": 2,
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"vocab_size": 30522
|
| 26 |
+
}
|
notebooks/results/checkpoint-2500/trainer_state.json
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.599488163787588,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.06397952655150352,
|
| 14 |
+
"grad_norm": 5.188015460968018,
|
| 15 |
+
"learning_rate": 4.8944337811900195e-05,
|
| 16 |
+
"loss": 0.5162,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.12795905310300704,
|
| 21 |
+
"grad_norm": 8.62886905670166,
|
| 22 |
+
"learning_rate": 4.7878012369375135e-05,
|
| 23 |
+
"loss": 0.4123,
|
| 24 |
+
"step": 200
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.19193857965451055,
|
| 28 |
+
"grad_norm": 6.661285877227783,
|
| 29 |
+
"learning_rate": 4.681168692685008e-05,
|
| 30 |
+
"loss": 0.4106,
|
| 31 |
+
"step": 300
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.2559181062060141,
|
| 35 |
+
"grad_norm": 7.992310523986816,
|
| 36 |
+
"learning_rate": 4.5745361484325014e-05,
|
| 37 |
+
"loss": 0.3619,
|
| 38 |
+
"step": 400
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.3198976327575176,
|
| 42 |
+
"grad_norm": 8.48903751373291,
|
| 43 |
+
"learning_rate": 4.467903604179996e-05,
|
| 44 |
+
"loss": 0.3724,
|
| 45 |
+
"step": 500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.3838771593090211,
|
| 49 |
+
"grad_norm": 7.3620219230651855,
|
| 50 |
+
"learning_rate": 4.3612710599274906e-05,
|
| 51 |
+
"loss": 0.3582,
|
| 52 |
+
"step": 600
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.44785668586052463,
|
| 56 |
+
"grad_norm": 7.127757549285889,
|
| 57 |
+
"learning_rate": 4.254638515674984e-05,
|
| 58 |
+
"loss": 0.351,
|
| 59 |
+
"step": 700
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.5118362124120281,
|
| 63 |
+
"grad_norm": 8.284778594970703,
|
| 64 |
+
"learning_rate": 4.1480059714224785e-05,
|
| 65 |
+
"loss": 0.3517,
|
| 66 |
+
"step": 800
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.5758157389635317,
|
| 70 |
+
"grad_norm": 6.389641284942627,
|
| 71 |
+
"learning_rate": 4.0413734271699725e-05,
|
| 72 |
+
"loss": 0.3197,
|
| 73 |
+
"step": 900
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.6397952655150352,
|
| 77 |
+
"grad_norm": 8.652924537658691,
|
| 78 |
+
"learning_rate": 3.9347408829174664e-05,
|
| 79 |
+
"loss": 0.3457,
|
| 80 |
+
"step": 1000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.7037747920665387,
|
| 84 |
+
"grad_norm": 9.87730598449707,
|
| 85 |
+
"learning_rate": 3.828108338664961e-05,
|
| 86 |
+
"loss": 0.3152,
|
| 87 |
+
"step": 1100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.7677543186180422,
|
| 91 |
+
"grad_norm": 9.235931396484375,
|
| 92 |
+
"learning_rate": 3.721475794412455e-05,
|
| 93 |
+
"loss": 0.3312,
|
| 94 |
+
"step": 1200
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.8317338451695457,
|
| 98 |
+
"grad_norm": 8.75272274017334,
|
| 99 |
+
"learning_rate": 3.614843250159949e-05,
|
| 100 |
+
"loss": 0.3098,
|
| 101 |
+
"step": 1300
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.8957133717210493,
|
| 105 |
+
"grad_norm": 3.6930184364318848,
|
| 106 |
+
"learning_rate": 3.508210705907443e-05,
|
| 107 |
+
"loss": 0.3057,
|
| 108 |
+
"step": 1400
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.9596928982725528,
|
| 112 |
+
"grad_norm": 15.71256160736084,
|
| 113 |
+
"learning_rate": 3.4015781616549375e-05,
|
| 114 |
+
"loss": 0.2994,
|
| 115 |
+
"step": 1500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 1.0236724248240563,
|
| 119 |
+
"grad_norm": 10.11008071899414,
|
| 120 |
+
"learning_rate": 3.2949456174024315e-05,
|
| 121 |
+
"loss": 0.2945,
|
| 122 |
+
"step": 1600
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.0876519513755598,
|
| 126 |
+
"grad_norm": 1.052371859550476,
|
| 127 |
+
"learning_rate": 3.1883130731499254e-05,
|
| 128 |
+
"loss": 0.2072,
|
| 129 |
+
"step": 1700
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.1516314779270633,
|
| 133 |
+
"grad_norm": 0.17214666306972504,
|
| 134 |
+
"learning_rate": 3.08168052889742e-05,
|
| 135 |
+
"loss": 0.1915,
|
| 136 |
+
"step": 1800
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 1.2156110044785668,
|
| 140 |
+
"grad_norm": 3.5573925971984863,
|
| 141 |
+
"learning_rate": 2.9750479846449137e-05,
|
| 142 |
+
"loss": 0.2268,
|
| 143 |
+
"step": 1900
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.2795905310300704,
|
| 147 |
+
"grad_norm": 12.984672546386719,
|
| 148 |
+
"learning_rate": 2.868415440392408e-05,
|
| 149 |
+
"loss": 0.1639,
|
| 150 |
+
"step": 2000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1.3435700575815739,
|
| 154 |
+
"grad_norm": 0.8138177990913391,
|
| 155 |
+
"learning_rate": 2.7617828961399022e-05,
|
| 156 |
+
"loss": 0.1866,
|
| 157 |
+
"step": 2100
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 1.4075495841330774,
|
| 161 |
+
"grad_norm": 10.373751640319824,
|
| 162 |
+
"learning_rate": 2.6551503518873962e-05,
|
| 163 |
+
"loss": 0.2171,
|
| 164 |
+
"step": 2200
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.471529110684581,
|
| 168 |
+
"grad_norm": 5.024399757385254,
|
| 169 |
+
"learning_rate": 2.5485178076348905e-05,
|
| 170 |
+
"loss": 0.1796,
|
| 171 |
+
"step": 2300
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.5355086372360844,
|
| 175 |
+
"grad_norm": 7.260871887207031,
|
| 176 |
+
"learning_rate": 2.4418852633823844e-05,
|
| 177 |
+
"loss": 0.1878,
|
| 178 |
+
"step": 2400
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 1.599488163787588,
|
| 182 |
+
"grad_norm": 6.540918350219727,
|
| 183 |
+
"learning_rate": 2.3352527191298784e-05,
|
| 184 |
+
"loss": 0.1675,
|
| 185 |
+
"step": 2500
|
| 186 |
+
}
|
| 187 |
+
],
|
| 188 |
+
"logging_steps": 100,
|
| 189 |
+
"max_steps": 4689,
|
| 190 |
+
"num_input_tokens_seen": 0,
|
| 191 |
+
"num_train_epochs": 3,
|
| 192 |
+
"save_steps": 500,
|
| 193 |
+
"stateful_callbacks": {
|
| 194 |
+
"TrainerControl": {
|
| 195 |
+
"args": {
|
| 196 |
+
"should_epoch_stop": false,
|
| 197 |
+
"should_evaluate": false,
|
| 198 |
+
"should_log": false,
|
| 199 |
+
"should_save": true,
|
| 200 |
+
"should_training_stop": false
|
| 201 |
+
},
|
| 202 |
+
"attributes": {}
|
| 203 |
+
}
|
| 204 |
+
},
|
| 205 |
+
"total_flos": 2630584331489280.0,
|
| 206 |
+
"train_batch_size": 16,
|
| 207 |
+
"trial_name": null,
|
| 208 |
+
"trial_params": null
|
| 209 |
+
}
|
notebooks/sentiment-bert-model/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e2f625868442cdfab87301d674b8ef829868c115ea620b96abf7864f34f3fc44
|
| 3 |
+
size 437958648
|
notebooks/sentiment-bert-model/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b158a7fd39c76db160cbdea68fa9ea7ba8a3a1d5a835ed6d7fc5813cda06fee
|
| 3 |
+
size 5649
|
sentiment-bert-model/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d55a2992e8ded638eaa281302a9c17000bab30d50c5f8af0a8e2c9872ec09115
|
| 3 |
+
size 876033163
|
sentiment-bert-model/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:415adf144042059d6a85669b9d40d3a9fa6f3a9a86c78bede7fab187ed7f2d87
|
| 3 |
+
size 14455
|
sentiment-bert-model/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d8929163a0ebc4f01d39af17027f2d6dea5f812ae44fb331640cdec84b38ff4
|
| 3 |
+
size 1465
|
sentiment-bert-model/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b158a7fd39c76db160cbdea68fa9ea7ba8a3a1d5a835ed6d7fc5813cda06fee
|
| 3 |
+
size 5649
|