Training in progress, step 20

{checkpoint-5 → checkpoint-10}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06d83a3b7096b6e62f9fee0da6bfbb5a2e2df2c8a079754f7bca55468755fd52
+oid sha256:5048ccd942c1fa8f84859abf13b3def087a58f67d403eb31ee5407850c2b73f0
 size 866630597

{checkpoint-5 → checkpoint-10}/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cae6739176a3473edae52ab21bb07019db3a2fc60c1037554d6c086b5cc1eed
+oid sha256:7663ee471abdc67aeda453f03e899ec561cb8b9163487ab6582d533f1aabe344
 size 433324849

{checkpoint-5 → checkpoint-10}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db1f438c6a150950f814259665b3d4e247652a538d0c2f02dbd1b14226004044
+oid sha256:19791385e49273a511907444b1ae61a0fb564d72d6c2f39e93faa8ba412a08bc
 size 14575

{checkpoint-5 → checkpoint-10}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34005622131fb69736c0d6692dfad44f92d65ea39ca103f193e4772227f9c86f
+oid sha256:300c86a2aa6e26efba7d9b0a68e362b00d4b32a365582d4ca0f1da2b053f668a
 size 627

{checkpoint-5 → checkpoint-10}/trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 0.17,
-  "best_model_checkpoint": "./trainer_test_checkpoint/checkpoint-5",
-  "epoch": 0.1,
-  "global_step": 5,
+  "best_metric": 0.25,
+  "best_model_checkpoint": "./trainer_test_checkpoint/checkpoint-10",
+  "epoch": 0.2,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -15,11 +15,20 @@
       "eval_samples_per_second": 28.444,
       "eval_steps_per_second": 14.222,
       "step": 5
+    },
+    {
+      "epoch": 0.2,
+      "eval_accuracy": 0.25,
+      "eval_loss": 1.7874902486801147,
+      "eval_runtime": 3.5523,
+      "eval_samples_per_second": 28.15,
+      "eval_steps_per_second": 14.075,
+      "step": 10
     }
   ],
   "max_steps": 100,
   "num_train_epochs": 2,
-  "total_flos": 2631181424640.0,
+  "total_flos": 5262362849280.0,
   "trial_name": null,
   "trial_params": null
 }

checkpoint-15/config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

checkpoint-15/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ba475c8d36049d825dc710ded8480d6d8fae3b32e0490f721ed506ed88a2da9
+size 866630597

checkpoint-15/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73546efd274884c910649f24f056089ff97f31d0bf3f3b12ed86f615860f3ac8
+size 433324849

checkpoint-15/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f76d54f18626b1e6a8c0c08bd80df27682d642ae62e823afbd857e1580073ffe
+size 14575

checkpoint-15/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1342d5172800147e9ebe25b8a1c9f4694b69157df8117f38d3567999ad3a36e5
+size 627

checkpoint-15/trainer_state.json

@@ -0,0 +1,43 @@
+{
+  "best_metric": 0.25,
+  "best_model_checkpoint": "./trainer_test_checkpoint/checkpoint-10",
+  "epoch": 0.3,
+  "global_step": 15,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "eval_accuracy": 0.17,
+      "eval_loss": 1.7631263732910156,
+      "eval_runtime": 3.5157,
+      "eval_samples_per_second": 28.444,
+      "eval_steps_per_second": 14.222,
+      "step": 5
+    },
+    {
+      "epoch": 0.2,
+      "eval_accuracy": 0.25,
+      "eval_loss": 1.7874902486801147,
+      "eval_runtime": 3.5523,
+      "eval_samples_per_second": 28.15,
+      "eval_steps_per_second": 14.075,
+      "step": 10
+    },
+    {
+      "epoch": 0.3,
+      "eval_accuracy": 0.2,
+      "eval_loss": 1.7714591026306152,
+      "eval_runtime": 5.4717,
+      "eval_samples_per_second": 18.276,
+      "eval_steps_per_second": 9.138,
+      "step": 15
+    }
+  ],
+  "max_steps": 100,
+  "num_train_epochs": 2,
+  "total_flos": 7893544273920.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-15/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f994e774f37ded33f3ebe64d3be2318670c8aaf6b944d3b012a125b991f2869c
+size 3963

checkpoint-20/config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

checkpoint-20/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b750a1285cf5d7330e810312588bf1673397d3409d08adf477c6d477a3f8648
+size 866630597

checkpoint-20/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0daebb71a520050584a0bd9e86481eb4fc646f7ea888e9af22035e1cca5702e6
+size 433324849

checkpoint-20/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c77f772a2ba9b5c0359e4c7dbaf1704b9f015e0cf13e2cc0d1557ec51f97467
+size 14575

checkpoint-20/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee02d9816945c904e881ed0c62a97354f538c50c767dfe7cddb585bcb191b22d
+size 627

checkpoint-20/trainer_state.json

@@ -0,0 +1,52 @@
+{
+  "best_metric": 0.25,
+  "best_model_checkpoint": "./trainer_test_checkpoint/checkpoint-10",
+  "epoch": 0.4,
+  "global_step": 20,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "eval_accuracy": 0.17,
+      "eval_loss": 1.7631263732910156,
+      "eval_runtime": 3.5157,
+      "eval_samples_per_second": 28.444,
+      "eval_steps_per_second": 14.222,
+      "step": 5
+    },
+    {
+      "epoch": 0.2,
+      "eval_accuracy": 0.25,
+      "eval_loss": 1.7874902486801147,
+      "eval_runtime": 3.5523,
+      "eval_samples_per_second": 28.15,
+      "eval_steps_per_second": 14.075,
+      "step": 10
+    },
+    {
+      "epoch": 0.3,
+      "eval_accuracy": 0.2,
+      "eval_loss": 1.7714591026306152,
+      "eval_runtime": 5.4717,
+      "eval_samples_per_second": 18.276,
+      "eval_steps_per_second": 9.138,
+      "step": 15
+    },
+    {
+      "epoch": 0.4,
+      "eval_accuracy": 0.2,
+      "eval_loss": 1.7414228916168213,
+      "eval_runtime": 3.5124,
+      "eval_samples_per_second": 28.47,
+      "eval_steps_per_second": 14.235,
+      "step": 20
+    }
+  ],
+  "max_steps": 100,
+  "num_train_epochs": 2,
+  "total_flos": 10524725698560.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-20/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f994e774f37ded33f3ebe64d3be2318670c8aaf6b944d3b012a125b991f2869c
+size 3963

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cae6739176a3473edae52ab21bb07019db3a2fc60c1037554d6c086b5cc1eed
+oid sha256:0daebb71a520050584a0bd9e86481eb4fc646f7ea888e9af22035e1cca5702e6
 size 433324849

runs/Aug01_08-59-35_bf9c8dab34e2/events.out.tfevents.1690880484.bf9c8dab34e2.4319.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4a09524187ab5ec5a44c29044b2cebd7448ab54a01f813ad02437f096bf8eb4
-size 4613
+oid sha256:d603590c421b8ccf248f628cbf3f8941e0e00bc2543c3ef99689d9fdb6289aea
+size 5564