Training in progress, step 12000, checkpoint

checkpoint-12000/config.json

@@ -0,0 +1,186 @@
+{
+  "_name_or_path": "NourFakih/Vit-GPT2-COCO2017Flickr-85k-09",
+  "architectures": [
+    "VisionEncoderDecoderModel"
+  ],
+  "bos_token_id": 50256,
+  "decoder": {
+    "_name_or_path": "",
+    "activation_function": "gelu_new",
+    "add_cross_attention": true,
+    "architectures": [
+      "GPT2LMHeadModel"
+    ],
+    "attn_pdrop": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 50256,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": 50256,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "embd_pdrop": 0.1,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 50256,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_epsilon": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "gpt2",
+    "n_ctx": 1024,
+    "n_embd": 768,
+    "n_head": 12,
+    "n_inner": null,
+    "n_layer": 12,
+    "n_positions": 1024,
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 50256,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "reorder_and_upcast_attn": false,
+    "repetition_penalty": 1.0,
+    "resid_pdrop": 0.1,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "scale_attn_by_inverse_layer_idx": false,
+    "scale_attn_weights": true,
+    "sep_token_id": null,
+    "summary_activation": null,
+    "summary_first_dropout": 0.1,
+    "summary_proj_to_labels": true,
+    "summary_type": "cls_index",
+    "summary_use_proj": true,
+    "suppress_tokens": null,
+    "task_specific_params": {
+      "text-generation": {
+        "do_sample": true,
+        "max_length": 50
+      }
+    },
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 50257
+  },
+  "decoder_start_token_id": 50256,
+  "encoder": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": [
+      "ViTModel"
+    ],
+    "attention_probs_dropout_prob": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "encoder_stride": 16,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 224,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "vit",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 16,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "qkv_bias": true,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "eos_token_id": 50256,
+  "is_encoder_decoder": true,
+  "model_type": "vision-encoder-decoder",
+  "pad_token_id": 50256,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2"
+}

checkpoint-12000/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 50256,
+  "decoder_start_token_id": 50256,
+  "eos_token_id": 50256,
+  "pad_token_id": 50256,
+  "transformers_version": "4.41.2"
+}

checkpoint-12000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e1e2c8926b5b1ad589776712f5efc4e55be25724d0ff2190441aab7e1c458de
+size 956835520

checkpoint-12000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:017b5b0623e50bc99fba87c0d746c8abe0a13d9b18b90d1488e59bcdae1c7484
+size 1909212608

checkpoint-12000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1df1610189133b58b9a815b0ef30e588f5b5f16bca02bc9773a74a900ef48aee
+size 14244

checkpoint-12000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b1d90a465f2d6b5626297140baca3decd1cf2991e90d02608778499d70ddd61
+size 1064

checkpoint-12000/trainer_state.json

@@ -0,0 +1,513 @@
+{
+  "best_metric": 0.510191798210144,
+  "best_model_checkpoint": "./Vit-GPT2-COCO2017Flickr-85k-09/checkpoint-4000",
+  "epoch": 2.2395259867500235,
+  "eval_steps": 500,
+  "global_step": 12000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09330969487729775,
+      "grad_norm": 1.1049598455429077,
+      "learning_rate": 4.8444693293517484e-05,
+      "loss": 0.2429,
+      "step": 500
+    },
+    {
+      "epoch": 0.09330969487729775,
+      "eval_gen_len": 11.738,
+      "eval_loss": 0.5351373553276062,
+      "eval_rouge1": 39.4446,
+      "eval_rouge2": 14.1599,
+      "eval_rougeL": 35.6123,
+      "eval_rougeLsum": 35.5846,
+      "eval_runtime": 463.8252,
+      "eval_samples_per_second": 8.624,
+      "eval_steps_per_second": 2.156,
+      "step": 500
+    },
+    {
+      "epoch": 0.1866193897545955,
+      "grad_norm": 1.1426328420639038,
+      "learning_rate": 4.6889386587034965e-05,
+      "loss": 0.2537,
+      "step": 1000
+    },
+    {
+      "epoch": 0.1866193897545955,
+      "eval_gen_len": 12.34875,
+      "eval_loss": 0.5301018357276917,
+      "eval_rouge1": 39.5332,
+      "eval_rouge2": 14.4745,
+      "eval_rougeL": 35.644,
+      "eval_rougeLsum": 35.6159,
+      "eval_runtime": 451.0336,
+      "eval_samples_per_second": 8.869,
+      "eval_steps_per_second": 2.217,
+      "step": 1000
+    },
+    {
+      "epoch": 0.27992908463189325,
+      "grad_norm": 1.017817735671997,
+      "learning_rate": 4.5334079880552446e-05,
+      "loss": 0.2564,
+      "step": 1500
+    },
+    {
+      "epoch": 0.27992908463189325,
+      "eval_gen_len": 12.2455,
+      "eval_loss": 0.5198264122009277,
+      "eval_rouge1": 39.8297,
+      "eval_rouge2": 14.555,
+      "eval_rougeL": 35.8598,
+      "eval_rougeLsum": 35.8344,
+      "eval_runtime": 446.7054,
+      "eval_samples_per_second": 8.954,
+      "eval_steps_per_second": 2.239,
+      "step": 1500
+    },
+    {
+      "epoch": 0.373238779509191,
+      "grad_norm": 0.9865152835845947,
+      "learning_rate": 4.3778773174069934e-05,
+      "loss": 0.2585,
+      "step": 2000
+    },
+    {
+      "epoch": 0.373238779509191,
+      "eval_gen_len": 11.8575,
+      "eval_loss": 0.5207428932189941,
+      "eval_rouge1": 39.4558,
+      "eval_rouge2": 14.0496,
+      "eval_rougeL": 35.5597,
+      "eval_rougeLsum": 35.526,
+      "eval_runtime": 441.2453,
+      "eval_samples_per_second": 9.065,
+      "eval_steps_per_second": 2.266,
+      "step": 2000
+    },
+    {
+      "epoch": 0.4665484743864888,
+      "grad_norm": 0.9201194047927856,
+      "learning_rate": 4.222346646758741e-05,
+      "loss": 0.2579,
+      "step": 2500
+    },
+    {
+      "epoch": 0.4665484743864888,
+      "eval_gen_len": 11.97325,
+      "eval_loss": 0.5187843441963196,
+      "eval_rouge1": 39.1359,
+      "eval_rouge2": 14.125,
+      "eval_rougeL": 35.4068,
+      "eval_rougeLsum": 35.3709,
+      "eval_runtime": 456.9413,
+      "eval_samples_per_second": 8.754,
+      "eval_steps_per_second": 2.188,
+      "step": 2500
+    },
+    {
+      "epoch": 0.5598581692637865,
+      "grad_norm": 1.011809229850769,
+      "learning_rate": 4.066815976110489e-05,
+      "loss": 0.2588,
+      "step": 3000
+    },
+    {
+      "epoch": 0.5598581692637865,
+      "eval_gen_len": 12.278,
+      "eval_loss": 0.5195733904838562,
+      "eval_rouge1": 39.0831,
+      "eval_rouge2": 14.0658,
+      "eval_rougeL": 35.4608,
+      "eval_rougeLsum": 35.4283,
+      "eval_runtime": 453.7444,
+      "eval_samples_per_second": 8.816,
+      "eval_steps_per_second": 2.204,
+      "step": 3000
+    },
+    {
+      "epoch": 0.6531678641410843,
+      "grad_norm": 0.9602178931236267,
+      "learning_rate": 3.911285305462237e-05,
+      "loss": 0.2618,
+      "step": 3500
+    },
+    {
+      "epoch": 0.6531678641410843,
+      "eval_gen_len": 11.99425,
+      "eval_loss": 0.5193876028060913,
+      "eval_rouge1": 39.751,
+      "eval_rouge2": 14.443,
+      "eval_rougeL": 36.076,
+      "eval_rougeLsum": 36.0475,
+      "eval_runtime": 451.6054,
+      "eval_samples_per_second": 8.857,
+      "eval_steps_per_second": 2.214,
+      "step": 3500
+    },
+    {
+      "epoch": 0.746477559018382,
+      "grad_norm": 1.0043072700500488,
+      "learning_rate": 3.755754634813985e-05,
+      "loss": 0.2579,
+      "step": 4000
+    },
+    {
+      "epoch": 0.746477559018382,
+      "eval_gen_len": 12.05125,
+      "eval_loss": 0.510191798210144,
+      "eval_rouge1": 39.7601,
+      "eval_rouge2": 14.5095,
+      "eval_rougeL": 36.0252,
+      "eval_rougeLsum": 35.9857,
+      "eval_runtime": 450.2804,
+      "eval_samples_per_second": 8.883,
+      "eval_steps_per_second": 2.221,
+      "step": 4000
+    },
+    {
+      "epoch": 0.8397872538956798,
+      "grad_norm": 0.9865091443061829,
+      "learning_rate": 3.600223964165734e-05,
+      "loss": 0.2569,
+      "step": 4500
+    },
+    {
+      "epoch": 0.8397872538956798,
+      "eval_gen_len": 11.64825,
+      "eval_loss": 0.5199217796325684,
+      "eval_rouge1": 39.398,
+      "eval_rouge2": 13.8871,
+      "eval_rougeL": 35.7218,
+      "eval_rougeLsum": 35.6911,
+      "eval_runtime": 440.2487,
+      "eval_samples_per_second": 9.086,
+      "eval_steps_per_second": 2.271,
+      "step": 4500
+    },
+    {
+      "epoch": 0.9330969487729776,
+      "grad_norm": 1.1134284734725952,
+      "learning_rate": 3.444693293517482e-05,
+      "loss": 0.253,
+      "step": 5000
+    },
+    {
+      "epoch": 0.9330969487729776,
+      "eval_gen_len": 12.01975,
+      "eval_loss": 0.5200353860855103,
+      "eval_rouge1": 39.8951,
+      "eval_rouge2": 14.4146,
+      "eval_rougeL": 35.883,
+      "eval_rougeLsum": 35.8507,
+      "eval_runtime": 445.4978,
+      "eval_samples_per_second": 8.979,
+      "eval_steps_per_second": 2.245,
+      "step": 5000
+    },
+    {
+      "epoch": 1.0264066436502752,
+      "grad_norm": 0.8591415286064148,
+      "learning_rate": 3.28916262286923e-05,
+      "loss": 0.2361,
+      "step": 5500
+    },
+    {
+      "epoch": 1.0264066436502752,
+      "eval_gen_len": 12.183,
+      "eval_loss": 0.560513973236084,
+      "eval_rouge1": 39.3352,
+      "eval_rouge2": 14.2234,
+      "eval_rougeL": 35.3107,
+      "eval_rougeLsum": 35.2772,
+      "eval_runtime": 451.5632,
+      "eval_samples_per_second": 8.858,
+      "eval_steps_per_second": 2.215,
+      "step": 5500
+    },
+    {
+      "epoch": 1.119716338527573,
+      "grad_norm": 0.9471074342727661,
+      "learning_rate": 3.1336319522209783e-05,
+      "loss": 0.2,
+      "step": 6000
+    },
+    {
+      "epoch": 1.119716338527573,
+      "eval_gen_len": 11.85975,
+      "eval_loss": 0.5701556205749512,
+      "eval_rouge1": 39.2184,
+      "eval_rouge2": 14.0096,
+      "eval_rougeL": 35.5475,
+      "eval_rougeLsum": 35.5042,
+      "eval_runtime": 443.3267,
+      "eval_samples_per_second": 9.023,
+      "eval_steps_per_second": 2.256,
+      "step": 6000
+    },
+    {
+      "epoch": 1.2130260334048708,
+      "grad_norm": 1.184536099433899,
+      "learning_rate": 2.978101281572726e-05,
+      "loss": 0.2034,
+      "step": 6500
+    },
+    {
+      "epoch": 1.2130260334048708,
+      "eval_gen_len": 11.878,
+      "eval_loss": 0.5543492436408997,
+      "eval_rouge1": 39.7118,
+      "eval_rouge2": 14.2757,
+      "eval_rougeL": 35.7613,
+      "eval_rougeLsum": 35.7316,
+      "eval_runtime": 448.2166,
+      "eval_samples_per_second": 8.924,
+      "eval_steps_per_second": 2.231,
+      "step": 6500
+    },
+    {
+      "epoch": 1.3063357282821686,
+      "grad_norm": 0.9648805260658264,
+      "learning_rate": 2.8225706109244742e-05,
+      "loss": 0.1968,
+      "step": 7000
+    },
+    {
+      "epoch": 1.3063357282821686,
+      "eval_gen_len": 12.1725,
+      "eval_loss": 0.5584425330162048,
+      "eval_rouge1": 39.1847,
+      "eval_rouge2": 13.9003,
+      "eval_rougeL": 35.3962,
+      "eval_rougeLsum": 35.3713,
+      "eval_runtime": 447.4882,
+      "eval_samples_per_second": 8.939,
+      "eval_steps_per_second": 2.235,
+      "step": 7000
+    },
+    {
+      "epoch": 1.3996454231594662,
+      "grad_norm": 1.0540575981140137,
+      "learning_rate": 2.6670399402762224e-05,
+      "loss": 0.1986,
+      "step": 7500
+    },
+    {
+      "epoch": 1.3996454231594662,
+      "eval_gen_len": 11.8395,
+      "eval_loss": 0.5572038292884827,
+      "eval_rouge1": 39.4428,
+      "eval_rouge2": 14.2672,
+      "eval_rougeL": 35.7359,
+      "eval_rougeLsum": 35.7093,
+      "eval_runtime": 437.4159,
+      "eval_samples_per_second": 9.145,
+      "eval_steps_per_second": 2.286,
+      "step": 7500
+    },
+    {
+      "epoch": 1.4930484277316414,
+      "grad_norm": 1.1180176734924316,
+      "learning_rate": 2.5115092696279708e-05,
+      "loss": 0.1988,
+      "step": 8000
+    },
+    {
+      "epoch": 1.4930484277316414,
+      "eval_gen_len": 11.99325,
+      "eval_loss": 0.555167019367218,
+      "eval_rouge1": 39.2719,
+      "eval_rouge2": 14.0411,
+      "eval_rougeL": 35.482,
+      "eval_rougeLsum": 35.4833,
+      "eval_runtime": 466.4795,
+      "eval_samples_per_second": 8.575,
+      "eval_steps_per_second": 2.144,
+      "step": 8000
+    },
+    {
+      "epoch": 1.5863581226089392,
+      "grad_norm": 0.9527018070220947,
+      "learning_rate": 2.355978598979719e-05,
+      "loss": 0.1971,
+      "step": 8500
+    },
+    {
+      "epoch": 1.5863581226089392,
+      "eval_gen_len": 12.10025,
+      "eval_loss": 0.5571706891059875,
+      "eval_rouge1": 39.2681,
+      "eval_rouge2": 14.1036,
+      "eval_rougeL": 35.4466,
+      "eval_rougeLsum": 35.4245,
+      "eval_runtime": 436.9857,
+      "eval_samples_per_second": 9.154,
+      "eval_steps_per_second": 2.288,
+      "step": 8500
+    },
+    {
+      "epoch": 1.6796678174862367,
+      "grad_norm": 0.9018421173095703,
+      "learning_rate": 2.200447928331467e-05,
+      "loss": 0.1978,
+      "step": 9000
+    },
+    {
+      "epoch": 1.6796678174862367,
+      "eval_gen_len": 12.11525,
+      "eval_loss": 0.5667414665222168,
+      "eval_rouge1": 39.2673,
+      "eval_rouge2": 14.0918,
+      "eval_rougeL": 35.4179,
+      "eval_rougeLsum": 35.4169,
+      "eval_runtime": 442.3098,
+      "eval_samples_per_second": 9.043,
+      "eval_steps_per_second": 2.261,
+      "step": 9000
+    },
+    {
+      "epoch": 1.7729775123635347,
+      "grad_norm": 0.8672216534614563,
+      "learning_rate": 2.0449172576832152e-05,
+      "loss": 0.1937,
+      "step": 9500
+    },
+    {
+      "epoch": 1.7729775123635347,
+      "eval_gen_len": 12.22075,
+      "eval_loss": 0.5781360864639282,
+      "eval_rouge1": 39.4115,
+      "eval_rouge2": 14.1115,
+      "eval_rougeL": 35.6952,
+      "eval_rougeLsum": 35.6834,
+      "eval_runtime": 444.1847,
+      "eval_samples_per_second": 9.005,
+      "eval_steps_per_second": 2.251,
+      "step": 9500
+    },
+    {
+      "epoch": 1.8662872072408323,
+      "grad_norm": 0.9997982382774353,
+      "learning_rate": 1.8893865870349633e-05,
+      "loss": 0.1897,
+      "step": 10000
+    },
+    {
+      "epoch": 1.8662872072408323,
+      "eval_gen_len": 11.88175,
+      "eval_loss": 0.5753504633903503,
+      "eval_rouge1": 39.2059,
+      "eval_rouge2": 14.076,
+      "eval_rougeL": 35.3392,
+      "eval_rougeLsum": 35.3332,
+      "eval_runtime": 437.0835,
+      "eval_samples_per_second": 9.152,
+      "eval_steps_per_second": 2.288,
+      "step": 10000
+    },
+    {
+      "epoch": 1.95959690211813,
+      "grad_norm": 2.3567240238189697,
+      "learning_rate": 1.7338559163867114e-05,
+      "loss": 0.1898,
+      "step": 10500
+    },
+    {
+      "epoch": 1.95959690211813,
+      "eval_gen_len": 11.88175,
+      "eval_loss": 0.5720392465591431,
+      "eval_rouge1": 39.4033,
+      "eval_rouge2": 14.1447,
+      "eval_rougeL": 35.598,
+      "eval_rougeLsum": 35.5976,
+      "eval_runtime": 448.1607,
+      "eval_samples_per_second": 8.925,
+      "eval_steps_per_second": 2.231,
+      "step": 10500
+    },
+    {
+      "epoch": 2.052906596995428,
+      "grad_norm": 1.1051445007324219,
+      "learning_rate": 1.57832524573846e-05,
+      "loss": 0.1685,
+      "step": 11000
+    },
+    {
+      "epoch": 2.052906596995428,
+      "eval_gen_len": 12.0585,
+      "eval_loss": 0.6186243891716003,
+      "eval_rouge1": 38.4626,
+      "eval_rouge2": 13.4695,
+      "eval_rougeL": 34.7378,
+      "eval_rougeLsum": 34.7294,
+      "eval_runtime": 439.923,
+      "eval_samples_per_second": 9.093,
+      "eval_steps_per_second": 2.273,
+      "step": 11000
+    },
+    {
+      "epoch": 2.1462162918727254,
+      "grad_norm": 1.2263615131378174,
+      "learning_rate": 1.4227945750902078e-05,
+      "loss": 0.1454,
+      "step": 11500
+    },
+    {
+      "epoch": 2.1462162918727254,
+      "eval_gen_len": 11.94475,
+      "eval_loss": 0.6147412657737732,
+      "eval_rouge1": 38.5335,
+      "eval_rouge2": 13.5152,
+      "eval_rougeL": 34.7075,
+      "eval_rougeLsum": 34.7033,
+      "eval_runtime": 434.2045,
+      "eval_samples_per_second": 9.212,
+      "eval_steps_per_second": 2.303,
+      "step": 11500
+    },
+    {
+      "epoch": 2.2395259867500235,
+      "grad_norm": 0.8852207660675049,
+      "learning_rate": 1.267263904441956e-05,
+      "loss": 0.1434,
+      "step": 12000
+    },
+    {
+      "epoch": 2.2395259867500235,
+      "eval_gen_len": 12.1855,
+      "eval_loss": 0.6229128241539001,
+      "eval_rouge1": 39.0044,
+      "eval_rouge2": 13.9276,
+      "eval_rougeL": 35.2226,
+      "eval_rougeLsum": 35.2116,
+      "eval_runtime": 439.4003,
+      "eval_samples_per_second": 9.103,
+      "eval_steps_per_second": 2.276,
+      "step": 12000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 16074,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.4648345239500095e+19,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-12000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:677bd07738c2b9da03770050cb823f5c2f7a2c7af17b864aee67c57b81936ff5
+size 5304