Training in progress, step 2173, checkpoint

checkpoint-2173/1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

checkpoint-2173/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

checkpoint-2173/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "bobox/DeBERTa-ST-AllLayers-v3-checkpoints-tmp",
+  "architectures": [
+    "DebertaV2Model"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

checkpoint-2173/config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.42.3",
+    "pytorch": "2.1.2"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

checkpoint-2173/modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

checkpoint-2173/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c604e48740955bb3d545f73c775ef2db0617a8d717c907b75bfb017fbb3d13cf
+size 1130520122

checkpoint-2173/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2805442560b3a1dcb9e77dd273661c9e3c783b770b293fce3f7845aeca68f4c8
+size 565251810

checkpoint-2173/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62f947b3e18c61c606973d61a5fe0f51800790a35a99f178feaad503e9d6a11e
+size 14244

checkpoint-2173/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d130c6d950bb9d1bd1d88f6eb419c831e070de70734295a7743fe7552353a06d
+size 1064

checkpoint-2173/sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

checkpoint-2173/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-2173/spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

checkpoint-2173/tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "stride": 0,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

checkpoint-2173/trainer_state.json

@@ -0,0 +1,523 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5,
+  "eval_steps": 1087,
+  "global_step": 2173,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012655315232397607,
+      "grad_norm": 29.207256317138672,
+      "learning_rate": 3.796594569719282e-07,
+      "loss": 0.6905,
+      "step": 55
+    },
+    {
+      "epoch": 0.025310630464795213,
+      "grad_norm": 14.99534797668457,
+      "learning_rate": 7.52416014726185e-07,
+      "loss": 0.4662,
+      "step": 110
+    },
+    {
+      "epoch": 0.03796594569719282,
+      "grad_norm": 10.413103103637695,
+      "learning_rate": 1.1320754716981131e-06,
+      "loss": 0.5361,
+      "step": 165
+    },
+    {
+      "epoch": 0.05062126092959043,
+      "grad_norm": 3.136443853378296,
+      "learning_rate": 1.5117349286700415e-06,
+      "loss": 0.642,
+      "step": 220
+    },
+    {
+      "epoch": 0.06327657616198804,
+      "grad_norm": 1.3601840734481812,
+      "learning_rate": 1.8913943856419695e-06,
+      "loss": 0.6881,
+      "step": 275
+    },
+    {
+      "epoch": 0.07593189139438564,
+      "grad_norm": 10.654134750366211,
+      "learning_rate": 2.271053842613898e-06,
+      "loss": 0.494,
+      "step": 330
+    },
+    {
+      "epoch": 0.08858720662678325,
+      "grad_norm": 11.055225372314453,
+      "learning_rate": 2.650713299585826e-06,
+      "loss": 0.6271,
+      "step": 385
+    },
+    {
+      "epoch": 0.10124252185918085,
+      "grad_norm": 18.74496841430664,
+      "learning_rate": 3.023469857340083e-06,
+      "loss": 0.5304,
+      "step": 440
+    },
+    {
+      "epoch": 0.11389783709157847,
+      "grad_norm": 8.764847755432129,
+      "learning_rate": 3.403129314312011e-06,
+      "loss": 0.5437,
+      "step": 495
+    },
+    {
+      "epoch": 0.12655315232397607,
+      "grad_norm": 15.166741371154785,
+      "learning_rate": 3.782788771283939e-06,
+      "loss": 0.6317,
+      "step": 550
+    },
+    {
+      "epoch": 0.13920846755637367,
+      "grad_norm": 7.722838401794434,
+      "learning_rate": 4.162448228255868e-06,
+      "loss": 0.7664,
+      "step": 605
+    },
+    {
+      "epoch": 0.15186378278877127,
+      "grad_norm": 11.76689624786377,
+      "learning_rate": 4.542107685227796e-06,
+      "loss": 0.5386,
+      "step": 660
+    },
+    {
+      "epoch": 0.1645190980211689,
+      "grad_norm": 2.6622166633605957,
+      "learning_rate": 4.921767142199724e-06,
+      "loss": 0.5238,
+      "step": 715
+    },
+    {
+      "epoch": 0.1771744132535665,
+      "grad_norm": 4.530745029449463,
+      "learning_rate": 5.301426599171652e-06,
+      "loss": 0.5771,
+      "step": 770
+    },
+    {
+      "epoch": 0.1898297284859641,
+      "grad_norm": 3.1290314197540283,
+      "learning_rate": 5.6810860561435805e-06,
+      "loss": 0.5162,
+      "step": 825
+    },
+    {
+      "epoch": 0.2024850437183617,
+      "grad_norm": 14.671398162841797,
+      "learning_rate": 6.060745513115509e-06,
+      "loss": 0.5143,
+      "step": 880
+    },
+    {
+      "epoch": 0.2151403589507593,
+      "grad_norm": 21.225963592529297,
+      "learning_rate": 6.440404970087437e-06,
+      "loss": 0.5172,
+      "step": 935
+    },
+    {
+      "epoch": 0.22779567418315694,
+      "grad_norm": 0.409208744764328,
+      "learning_rate": 6.820064427059365e-06,
+      "loss": 0.539,
+      "step": 990
+    },
+    {
+      "epoch": 0.24045098941555454,
+      "grad_norm": 5.888367652893066,
+      "learning_rate": 7.199723884031293e-06,
+      "loss": 0.3987,
+      "step": 1045
+    },
+    {
+      "epoch": 0.2501150483202945,
+      "eval_StS-test_pearson_cosine": 0.8796347799632783,
+      "eval_StS-test_pearson_dot": 0.7952693748718531,
+      "eval_StS-test_pearson_euclidean": 0.8662889333214727,
+      "eval_StS-test_pearson_manhattan": 0.8673292515085165,
+      "eval_StS-test_pearson_max": 0.8796347799632783,
+      "eval_StS-test_spearman_cosine": 0.8923792178697394,
+      "eval_StS-test_spearman_dot": 0.8035752306525754,
+      "eval_StS-test_spearman_euclidean": 0.867901651872447,
+      "eval_StS-test_spearman_manhattan": 0.8708405624162647,
+      "eval_StS-test_spearman_max": 0.8923792178697394,
+      "eval_Vitaminc-test_cosine_accuracy": 0.5710526315789474,
+      "eval_Vitaminc-test_cosine_accuracy_threshold": 0.717450737953186,
+      "eval_Vitaminc-test_cosine_ap": 0.5613681349794449,
+      "eval_Vitaminc-test_cosine_f1": 0.6779026217228464,
+      "eval_Vitaminc-test_cosine_f1_threshold": 0.4914843738079071,
+      "eval_Vitaminc-test_cosine_precision": 0.5186246418338109,
+      "eval_Vitaminc-test_cosine_recall": 0.9783783783783784,
+      "eval_Vitaminc-test_dot_accuracy": 0.5631578947368421,
+      "eval_Vitaminc-test_dot_accuracy_threshold": 22.15652847290039,
+      "eval_Vitaminc-test_dot_ap": 0.5440593805944962,
+      "eval_Vitaminc-test_dot_f1": 0.6703910614525139,
+      "eval_Vitaminc-test_dot_f1_threshold": 13.749557495117188,
+      "eval_Vitaminc-test_dot_precision": 0.5113636363636364,
+      "eval_Vitaminc-test_dot_recall": 0.972972972972973,
+      "eval_Vitaminc-test_euclidean_accuracy": 0.5894736842105263,
+      "eval_Vitaminc-test_euclidean_accuracy_threshold": 4.052872657775879,
+      "eval_Vitaminc-test_euclidean_ap": 0.5530280125387326,
+      "eval_Vitaminc-test_euclidean_f1": 0.6654676258992805,
+      "eval_Vitaminc-test_euclidean_f1_threshold": 7.110843658447266,
+      "eval_Vitaminc-test_euclidean_precision": 0.49865229110512127,
+      "eval_Vitaminc-test_euclidean_recall": 1.0,
+      "eval_Vitaminc-test_manhattan_accuracy": 0.5815789473684211,
+      "eval_Vitaminc-test_manhattan_accuracy_threshold": 82.38890075683594,
+      "eval_Vitaminc-test_manhattan_ap": 0.5516886870709616,
+      "eval_Vitaminc-test_manhattan_f1": 0.6642728904847397,
+      "eval_Vitaminc-test_manhattan_f1_threshold": 147.61215209960938,
+      "eval_Vitaminc-test_manhattan_precision": 0.49731182795698925,
+      "eval_Vitaminc-test_manhattan_recall": 1.0,
+      "eval_Vitaminc-test_max_accuracy": 0.5894736842105263,
+      "eval_Vitaminc-test_max_accuracy_threshold": 82.38890075683594,
+      "eval_Vitaminc-test_max_ap": 0.5613681349794449,
+      "eval_Vitaminc-test_max_f1": 0.6779026217228464,
+      "eval_Vitaminc-test_max_f1_threshold": 147.61215209960938,
+      "eval_Vitaminc-test_max_precision": 0.5186246418338109,
+      "eval_Vitaminc-test_max_recall": 1.0,
+      "eval_mrpc-test_cosine_accuracy": 0.7578947368421053,
+      "eval_mrpc-test_cosine_accuracy_threshold": 0.6727536916732788,
+      "eval_mrpc-test_cosine_ap": 0.8587001102740125,
+      "eval_mrpc-test_cosine_f1": 0.8397212543554007,
+      "eval_mrpc-test_cosine_f1_threshold": 0.6727536916732788,
+      "eval_mrpc-test_cosine_precision": 0.7392638036809815,
+      "eval_mrpc-test_cosine_recall": 0.9717741935483871,
+      "eval_mrpc-test_dot_accuracy": 0.7078947368421052,
+      "eval_mrpc-test_dot_accuracy_threshold": 16.11664390563965,
+      "eval_mrpc-test_dot_ap": 0.8100266677537138,
+      "eval_mrpc-test_dot_f1": 0.810810810810811,
+      "eval_mrpc-test_dot_f1_threshold": 13.418485641479492,
+      "eval_mrpc-test_dot_precision": 0.6976744186046512,
+      "eval_mrpc-test_dot_recall": 0.967741935483871,
+      "eval_mrpc-test_euclidean_accuracy": 0.7315789473684211,
+      "eval_mrpc-test_euclidean_accuracy_threshold": 3.678903102874756,
+      "eval_mrpc-test_euclidean_ap": 0.8265125766382443,
+      "eval_mrpc-test_euclidean_f1": 0.8111111111111112,
+      "eval_mrpc-test_euclidean_f1_threshold": 3.678903102874756,
+      "eval_mrpc-test_euclidean_precision": 0.75,
+      "eval_mrpc-test_euclidean_recall": 0.8830645161290323,
+      "eval_mrpc-test_manhattan_accuracy": 0.7263157894736842,
+      "eval_mrpc-test_manhattan_accuracy_threshold": 71.4499740600586,
+      "eval_mrpc-test_manhattan_ap": 0.8234340325662497,
+      "eval_mrpc-test_manhattan_f1": 0.8114901256732495,
+      "eval_mrpc-test_manhattan_f1_threshold": 76.88587951660156,
+      "eval_mrpc-test_manhattan_precision": 0.7313915857605178,
+      "eval_mrpc-test_manhattan_recall": 0.9112903225806451,
+      "eval_mrpc-test_max_accuracy": 0.7578947368421053,
+      "eval_mrpc-test_max_accuracy_threshold": 71.4499740600586,
+      "eval_mrpc-test_max_ap": 0.8587001102740125,
+      "eval_mrpc-test_max_f1": 0.8397212543554007,
+      "eval_mrpc-test_max_f1_threshold": 76.88587951660156,
+      "eval_mrpc-test_max_precision": 0.75,
+      "eval_mrpc-test_max_recall": 0.9717741935483871,
+      "eval_nli-pairs_loss": 0.8454961180686951,
+      "eval_nli-pairs_runtime": 3.0755,
+      "eval_nli-pairs_samples_per_second": 52.023,
+      "eval_nli-pairs_steps_per_second": 1.626,
+      "eval_sequential_score": 0.5613681349794449,
+      "step": 1087
+    },
+    {
+      "epoch": 0.2501150483202945,
+      "eval_vitaminc-pairs_loss": 4.881535053253174,
+      "eval_vitaminc-pairs_runtime": 2.1499,
+      "eval_vitaminc-pairs_samples_per_second": 74.421,
+      "eval_vitaminc-pairs_steps_per_second": 2.326,
+      "step": 1087
+    },
+    {
+      "epoch": 0.2501150483202945,
+      "eval_qnli-contrastive_loss": 0.12381808459758759,
+      "eval_qnli-contrastive_runtime": 0.5267,
+      "eval_qnli-contrastive_samples_per_second": 303.788,
+      "eval_qnli-contrastive_steps_per_second": 9.493,
+      "step": 1087
+    },
+    {
+      "epoch": 0.2501150483202945,
+      "eval_scitail-pairs-qa_loss": 0.07101307064294815,
+      "eval_scitail-pairs-qa_runtime": 1.3518,
+      "eval_scitail-pairs-qa_samples_per_second": 118.358,
+      "eval_scitail-pairs-qa_steps_per_second": 3.699,
+      "step": 1087
+    },
+    {
+      "epoch": 0.2501150483202945,
+      "eval_scitail-pairs-pos_loss": 0.40993720293045044,
+      "eval_scitail-pairs-pos_runtime": 2.366,
+      "eval_scitail-pairs-pos_samples_per_second": 67.626,
+      "eval_scitail-pairs-pos_steps_per_second": 2.113,
+      "step": 1087
+    },
+    {
+      "epoch": 0.2501150483202945,
+      "eval_xsum-pairs_loss": 0.2330073118209839,
+      "eval_xsum-pairs_runtime": 1.4296,
+      "eval_xsum-pairs_samples_per_second": 111.919,
+      "eval_xsum-pairs_steps_per_second": 3.497,
+      "step": 1087
+    },
+    {
+      "epoch": 0.2501150483202945,
+      "eval_compression-pairs_loss": 0.08333557099103928,
+      "eval_compression-pairs_runtime": 0.4781,
+      "eval_compression-pairs_samples_per_second": 334.651,
+      "eval_compression-pairs_steps_per_second": 10.458,
+      "step": 1087
+    },
+    {
+      "epoch": 0.2501150483202945,
+      "eval_sciq_pairs_loss": 0.24275392293930054,
+      "eval_sciq_pairs_runtime": 7.6927,
+      "eval_sciq_pairs_samples_per_second": 20.799,
+      "eval_sciq_pairs_steps_per_second": 0.65,
+      "step": 1087
+    },
+    {
+      "epoch": 0.2501150483202945,
+      "eval_qasc_pairs_loss": 0.22381672263145447,
+      "eval_qasc_pairs_runtime": 1.4917,
+      "eval_qasc_pairs_samples_per_second": 107.258,
+      "eval_qasc_pairs_steps_per_second": 3.352,
+      "step": 1087
+    },
+    {
+      "epoch": 0.2501150483202945,
+      "eval_qasc_facts_sym_loss": 0.11455042660236359,
+      "eval_qasc_facts_sym_runtime": 0.3427,
+      "eval_qasc_facts_sym_samples_per_second": 466.845,
+      "eval_qasc_facts_sym_steps_per_second": 14.589,
+      "step": 1087
+    },
+    {
+      "epoch": 0.2501150483202945,
+      "eval_openbookqa_pairs_loss": 1.7258867025375366,
+      "eval_openbookqa_pairs_runtime": 1.2536,
+      "eval_openbookqa_pairs_samples_per_second": 127.631,
+      "eval_openbookqa_pairs_steps_per_second": 3.988,
+      "step": 1087
+    },
+    {
+      "epoch": 0.2501150483202945,
+      "eval_msmarco_pairs_loss": 0.5000651478767395,
+      "eval_msmarco_pairs_runtime": 3.2185,
+      "eval_msmarco_pairs_samples_per_second": 49.713,
+      "eval_msmarco_pairs_steps_per_second": 1.554,
+      "step": 1087
+    },
+    {
+      "epoch": 0.2501150483202945,
+      "eval_nq_pairs_loss": 0.4875173568725586,
+      "eval_nq_pairs_runtime": 6.1488,
+      "eval_nq_pairs_samples_per_second": 26.022,
+      "eval_nq_pairs_steps_per_second": 0.813,
+      "step": 1087
+    },
+    {
+      "epoch": 0.2501150483202945,
+      "eval_trivia_pairs_loss": 0.45671015977859497,
+      "eval_trivia_pairs_runtime": 10.2361,
+      "eval_trivia_pairs_samples_per_second": 15.631,
+      "eval_trivia_pairs_steps_per_second": 0.488,
+      "step": 1087
+    },
+    {
+      "epoch": 0.2501150483202945,
+      "eval_quora_pairs_loss": 0.12006044387817383,
+      "eval_quora_pairs_runtime": 0.93,
+      "eval_quora_pairs_samples_per_second": 172.036,
+      "eval_quora_pairs_steps_per_second": 5.376,
+      "step": 1087
+    },
+    {
+      "epoch": 0.2501150483202945,
+      "eval_gooaq_pairs_loss": 0.6029041409492493,
+      "eval_gooaq_pairs_runtime": 2.0734,
+      "eval_gooaq_pairs_samples_per_second": 77.167,
+      "eval_gooaq_pairs_steps_per_second": 2.411,
+      "step": 1087
+    },
+    {
+      "epoch": 0.2501150483202945,
+      "eval_mrpc_pairs_loss": 0.04627904295921326,
+      "eval_mrpc_pairs_runtime": 0.3808,
+      "eval_mrpc_pairs_samples_per_second": 420.151,
+      "eval_mrpc_pairs_steps_per_second": 13.13,
+      "step": 1087
+    },
+    {
+      "epoch": 0.25310630464795214,
+      "grad_norm": 5.187383651733398,
+      "learning_rate": 7.579383341003222e-06,
+      "loss": 0.5964,
+      "step": 1100
+    },
+    {
+      "epoch": 0.26576161988034974,
+      "grad_norm": 15.151920318603516,
+      "learning_rate": 7.95904279797515e-06,
+      "loss": 0.5515,
+      "step": 1155
+    },
+    {
+      "epoch": 0.27841693511274734,
+      "grad_norm": 21.508556365966797,
+      "learning_rate": 8.338702254947079e-06,
+      "loss": 0.4783,
+      "step": 1210
+    },
+    {
+      "epoch": 0.29107225034514494,
+      "grad_norm": 9.393538475036621,
+      "learning_rate": 8.718361711919006e-06,
+      "loss": 0.6334,
+      "step": 1265
+    },
+    {
+      "epoch": 0.30372756557754255,
+      "grad_norm": 11.627140045166016,
+      "learning_rate": 9.098021168890933e-06,
+      "loss": 0.51,
+      "step": 1320
+    },
+    {
+      "epoch": 0.31638288080994015,
+      "grad_norm": 13.188899993896484,
+      "learning_rate": 9.477680625862863e-06,
+      "loss": 0.5821,
+      "step": 1375
+    },
+    {
+      "epoch": 0.3290381960423378,
+      "grad_norm": 1.8294838666915894,
+      "learning_rate": 9.85734008283479e-06,
+      "loss": 0.416,
+      "step": 1430
+    },
+    {
+      "epoch": 0.3416935112747354,
+      "grad_norm": 32.063167572021484,
+      "learning_rate": 1.0236999539806719e-05,
+      "loss": 0.6191,
+      "step": 1485
+    },
+    {
+      "epoch": 0.354348826507133,
+      "grad_norm": 8.023995399475098,
+      "learning_rate": 1.0616658996778646e-05,
+      "loss": 0.5167,
+      "step": 1540
+    },
+    {
+      "epoch": 0.3670041417395306,
+      "grad_norm": 13.192673683166504,
+      "learning_rate": 1.0996318453750575e-05,
+      "loss": 0.5405,
+      "step": 1595
+    },
+    {
+      "epoch": 0.3796594569719282,
+      "grad_norm": 0.5318098068237305,
+      "learning_rate": 1.1375977910722504e-05,
+      "loss": 0.6837,
+      "step": 1650
+    },
+    {
+      "epoch": 0.3923147722043258,
+      "grad_norm": 17.35649299621582,
+      "learning_rate": 1.1755637367694432e-05,
+      "loss": 0.5547,
+      "step": 1705
+    },
+    {
+      "epoch": 0.4049700874367234,
+      "grad_norm": 8.649995803833008,
+      "learning_rate": 1.213529682466636e-05,
+      "loss": 0.6971,
+      "step": 1760
+    },
+    {
+      "epoch": 0.417625402669121,
+      "grad_norm": 10.77607536315918,
+      "learning_rate": 1.2514956281638288e-05,
+      "loss": 0.6149,
+      "step": 1815
+    },
+    {
+      "epoch": 0.4302807179015186,
+      "grad_norm": 0.6141108274459839,
+      "learning_rate": 1.2894615738610217e-05,
+      "loss": 0.5569,
+      "step": 1870
+    },
+    {
+      "epoch": 0.4429360331339162,
+      "grad_norm": 14.11988353729248,
+      "learning_rate": 1.3274275195582145e-05,
+      "loss": 0.6145,
+      "step": 1925
+    },
+    {
+      "epoch": 0.4555913483663139,
+      "grad_norm": 14.13809585571289,
+      "learning_rate": 1.3653934652554072e-05,
+      "loss": 0.6826,
+      "step": 1980
+    },
+    {
+      "epoch": 0.4682466635987115,
+      "grad_norm": 1.9349863529205322,
+      "learning_rate": 1.4033594109526001e-05,
+      "loss": 0.6285,
+      "step": 2035
+    },
+    {
+      "epoch": 0.4809019788311091,
+      "grad_norm": 12.279942512512207,
+      "learning_rate": 1.4413253566497928e-05,
+      "loss": 0.739,
+      "step": 2090
+    },
+    {
+      "epoch": 0.4935572940635067,
+      "grad_norm": 5.102914810180664,
+      "learning_rate": 1.4792913023469859e-05,
+      "loss": 0.6119,
+      "step": 2145
+    }
+  ],
+  "logging_steps": 55,
+  "max_steps": 21730,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 2173,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2173/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9308542e122da3acf799698478fe93f63192bc8420814e7f5402c992b9e10b4e
+size 5624