End of training

checkpoint-320/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:545aa19eb4410fc3feed598b75c981bfdcbb6c952229824c6bd1b04e161f9f84
-size 737788917

checkpoint-320/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6b3143a2798a49b9dcf15a141512c86b6add165baf4f859e660e7985e9d40e60
-size 14575

checkpoint-320/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:29ea6a10a633bcfa1c650a32be0ea72bf6870f43bc564bbaa5c04ac08767fab3
-size 627

checkpoint-320/trainer_state.json

@@ -1,334 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 32.0,
-  "global_step": 320,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.1,
-      "learning_rate": 1.9960000000000002e-05,
-      "loss": 2.314,
-      "step": 1
-    },
-    {
-      "epoch": 2.5,
-      "learning_rate": 1.9e-05,
-      "loss": 2.311,
-      "step": 25
-    },
-    {
-      "epoch": 2.5,
-      "eval_accuracy": 0.15,
-      "eval_disk_space_total": 78.1898422241211,
-      "eval_disk_space_used": 36.27968215942383,
-      "eval_f1": 0.08571428571428572,
-      "eval_gpu_ram_allocated": 4.843059062957764,
-      "eval_gpu_ram_cached": 7.046875,
-      "eval_gpu_ram_total": 39.56402587890625,
-      "eval_gpu_utilization": 40,
-      "eval_loss": 2.3033015727996826,
-      "eval_precision": 0.11052631578947367,
-      "eval_recall": 0.15,
-      "eval_runtime": 0.2186,
-      "eval_samples_per_second": 91.494,
-      "eval_steps_per_second": 13.724,
-      "eval_system_ram_total": 83.48074722290039,
-      "eval_system_ram_used": 5.000797271728516,
-      "step": 25
-    },
-    {
-      "epoch": 5.0,
-      "learning_rate": 1.8e-05,
-      "loss": 2.2703,
-      "step": 50
-    },
-    {
-      "epoch": 5.0,
-      "eval_accuracy": 0.2,
-      "eval_disk_space_total": 78.1898422241211,
-      "eval_disk_space_used": 36.279693603515625,
-      "eval_f1": 0.06857142857142857,
-      "eval_gpu_ram_allocated": 4.843057632446289,
-      "eval_gpu_ram_cached": 7.046875,
-      "eval_gpu_ram_total": 39.56402587890625,
-      "eval_gpu_utilization": 38,
-      "eval_loss": 2.3011314868927,
-      "eval_precision": 0.041666666666666664,
-      "eval_recall": 0.2,
-      "eval_runtime": 0.2293,
-      "eval_samples_per_second": 87.241,
-      "eval_steps_per_second": 13.086,
-      "eval_system_ram_total": 83.48074722290039,
-      "eval_system_ram_used": 5.012126922607422,
-      "step": 50
-    },
-    {
-      "epoch": 7.5,
-      "learning_rate": 1.704e-05,
-      "loss": 2.0062,
-      "step": 75
-    },
-    {
-      "epoch": 7.5,
-      "eval_accuracy": 0.15,
-      "eval_disk_space_total": 78.1898422241211,
-      "eval_disk_space_used": 36.27973175048828,
-      "eval_f1": 0.07936507936507937,
-      "eval_gpu_ram_allocated": 4.843067646026611,
-      "eval_gpu_ram_cached": 7.046875,
-      "eval_gpu_ram_total": 39.56402587890625,
-      "eval_gpu_utilization": 42,
-      "eval_loss": 2.2817370891571045,
-      "eval_precision": 0.05428571428571429,
-      "eval_recall": 0.15,
-      "eval_runtime": 0.208,
-      "eval_samples_per_second": 96.173,
-      "eval_steps_per_second": 14.426,
-      "eval_system_ram_total": 83.48074722290039,
-      "eval_system_ram_used": 4.985599517822266,
-      "step": 75
-    },
-    {
-      "epoch": 10.0,
-      "learning_rate": 1.6040000000000002e-05,
-      "loss": 1.49,
-      "step": 100
-    },
-    {
-      "epoch": 10.0,
-      "eval_accuracy": 0.2,
-      "eval_disk_space_total": 78.1898422241211,
-      "eval_disk_space_used": 36.27973556518555,
-      "eval_f1": 0.11777777777777779,
-      "eval_gpu_ram_allocated": 4.843059062957764,
-      "eval_gpu_ram_cached": 7.046875,
-      "eval_gpu_ram_total": 39.56402587890625,
-      "eval_gpu_utilization": 37,
-      "eval_loss": 2.3280632495880127,
-      "eval_precision": 0.0869047619047619,
-      "eval_recall": 0.2,
-      "eval_runtime": 0.208,
-      "eval_samples_per_second": 96.137,
-      "eval_steps_per_second": 14.421,
-      "eval_system_ram_total": 83.48074722290039,
-      "eval_system_ram_used": 4.982398986816406,
-      "step": 100
-    },
-    {
-      "epoch": 12.5,
-      "learning_rate": 1.5040000000000002e-05,
-      "loss": 0.9424,
-      "step": 125
-    },
-    {
-      "epoch": 12.5,
-      "eval_accuracy": 0.25,
-      "eval_disk_space_total": 78.1898422241211,
-      "eval_disk_space_used": 36.27980041503906,
-      "eval_f1": 0.17333333333333334,
-      "eval_gpu_ram_allocated": 4.843059062957764,
-      "eval_gpu_ram_cached": 7.046875,
-      "eval_gpu_ram_total": 39.56402587890625,
-      "eval_gpu_utilization": 42,
-      "eval_loss": 2.3475446701049805,
-      "eval_precision": 0.14166666666666666,
-      "eval_recall": 0.25,
-      "eval_runtime": 0.2046,
-      "eval_samples_per_second": 97.736,
-      "eval_steps_per_second": 14.66,
-      "eval_system_ram_total": 83.48074722290039,
-      "eval_system_ram_used": 4.944629669189453,
-      "step": 125
-    },
-    {
-      "epoch": 15.0,
-      "learning_rate": 1.4040000000000001e-05,
-      "loss": 0.5591,
-      "step": 150
-    },
-    {
-      "epoch": 15.0,
-      "eval_accuracy": 0.25,
-      "eval_disk_space_total": 78.1898422241211,
-      "eval_disk_space_used": 36.27981948852539,
-      "eval_f1": 0.17444444444444446,
-      "eval_gpu_ram_allocated": 4.843059062957764,
-      "eval_gpu_ram_cached": 7.046875,
-      "eval_gpu_ram_total": 39.56402587890625,
-      "eval_gpu_utilization": 29,
-      "eval_loss": 2.4503185749053955,
-      "eval_precision": 0.14523809523809522,
-      "eval_recall": 0.25,
-      "eval_runtime": 0.2141,
-      "eval_samples_per_second": 93.429,
-      "eval_steps_per_second": 14.014,
-      "eval_system_ram_total": 83.48074722290039,
-      "eval_system_ram_used": 4.920143127441406,
-      "step": 150
-    },
-    {
-      "epoch": 17.5,
-      "learning_rate": 1.3080000000000002e-05,
-      "loss": 0.2893,
-      "step": 175
-    },
-    {
-      "epoch": 17.5,
-      "eval_accuracy": 0.25,
-      "eval_disk_space_total": 78.1898422241211,
-      "eval_disk_space_used": 36.27982711791992,
-      "eval_f1": 0.17444444444444446,
-      "eval_gpu_ram_allocated": 4.843067646026611,
-      "eval_gpu_ram_cached": 7.046875,
-      "eval_gpu_ram_total": 39.56402587890625,
-      "eval_gpu_utilization": 43,
-      "eval_loss": 2.555687665939331,
-      "eval_precision": 0.14523809523809522,
-      "eval_recall": 0.25,
-      "eval_runtime": 0.2265,
-      "eval_samples_per_second": 88.288,
-      "eval_steps_per_second": 13.243,
-      "eval_system_ram_total": 83.48074722290039,
-      "eval_system_ram_used": 4.961811065673828,
-      "step": 175
-    },
-    {
-      "epoch": 20.0,
-      "learning_rate": 1.2080000000000001e-05,
-      "loss": 0.1623,
-      "step": 200
-    },
-    {
-      "epoch": 20.0,
-      "eval_accuracy": 0.3,
-      "eval_disk_space_total": 78.1898422241211,
-      "eval_disk_space_used": 36.279876708984375,
-      "eval_f1": 0.2411111111111111,
-      "eval_gpu_ram_allocated": 4.843057632446289,
-      "eval_gpu_ram_cached": 7.046875,
-      "eval_gpu_ram_total": 39.56402587890625,
-      "eval_gpu_utilization": 30,
-      "eval_loss": 2.621793270111084,
-      "eval_precision": 0.2452380952380952,
-      "eval_recall": 0.3,
-      "eval_runtime": 0.217,
-      "eval_samples_per_second": 92.146,
-      "eval_steps_per_second": 13.822,
-      "eval_system_ram_total": 83.48074722290039,
-      "eval_system_ram_used": 4.910972595214844,
-      "step": 200
-    },
-    {
-      "epoch": 22.5,
-      "learning_rate": 1.1080000000000002e-05,
-      "loss": 0.0817,
-      "step": 225
-    },
-    {
-      "epoch": 22.5,
-      "eval_accuracy": 0.3,
-      "eval_disk_space_total": 78.1898422241211,
-      "eval_disk_space_used": 36.279930114746094,
-      "eval_f1": 0.24,
-      "eval_gpu_ram_allocated": 4.843059062957764,
-      "eval_gpu_ram_cached": 7.046875,
-      "eval_gpu_ram_total": 39.56402587890625,
-      "eval_gpu_utilization": 38,
-      "eval_loss": 2.734551191329956,
-      "eval_precision": 0.24166666666666664,
-      "eval_recall": 0.3,
-      "eval_runtime": 0.2092,
-      "eval_samples_per_second": 95.586,
-      "eval_steps_per_second": 14.338,
-      "eval_system_ram_total": 83.48074722290039,
-      "eval_system_ram_used": 4.941272735595703,
-      "step": 225
-    },
-    {
-      "epoch": 25.0,
-      "learning_rate": 1.008e-05,
-      "loss": 0.0475,
-      "step": 250
-    },
-    {
-      "epoch": 25.0,
-      "eval_accuracy": 0.3,
-      "eval_disk_space_total": 78.1898422241211,
-      "eval_disk_space_used": 36.27995300292969,
-      "eval_f1": 0.23444444444444446,
-      "eval_gpu_ram_allocated": 4.843059062957764,
-      "eval_gpu_ram_cached": 7.046875,
-      "eval_gpu_ram_total": 39.56402587890625,
-      "eval_gpu_utilization": 40,
-      "eval_loss": 2.9325406551361084,
-      "eval_precision": 0.23690476190476187,
-      "eval_recall": 0.3,
-      "eval_runtime": 0.2145,
-      "eval_samples_per_second": 93.259,
-      "eval_steps_per_second": 13.989,
-      "eval_system_ram_total": 83.48074722290039,
-      "eval_system_ram_used": 4.931392669677734,
-      "step": 250
-    },
-    {
-      "epoch": 27.5,
-      "learning_rate": 9.080000000000001e-06,
-      "loss": 0.0322,
-      "step": 275
-    },
-    {
-      "epoch": 27.5,
-      "eval_accuracy": 0.3,
-      "eval_disk_space_total": 78.1898422241211,
-      "eval_disk_space_used": 36.28001403808594,
-      "eval_f1": 0.2511111111111112,
-      "eval_gpu_ram_allocated": 4.843059062957764,
-      "eval_gpu_ram_cached": 7.046875,
-      "eval_gpu_ram_total": 39.56402587890625,
-      "eval_gpu_utilization": 42,
-      "eval_loss": 3.123502254486084,
-      "eval_precision": 0.2869047619047619,
-      "eval_recall": 0.3,
-      "eval_runtime": 0.2104,
-      "eval_samples_per_second": 95.043,
-      "eval_steps_per_second": 14.256,
-      "eval_system_ram_total": 83.48074722290039,
-      "eval_system_ram_used": 4.933628082275391,
-      "step": 275
-    },
-    {
-      "epoch": 30.0,
-      "learning_rate": 8.08e-06,
-      "loss": 0.0254,
-      "step": 300
-    },
-    {
-      "epoch": 30.0,
-      "eval_accuracy": 0.3,
-      "eval_disk_space_total": 78.1898422241211,
-      "eval_disk_space_used": 36.280025482177734,
-      "eval_f1": 0.23444444444444446,
-      "eval_gpu_ram_allocated": 4.843059062957764,
-      "eval_gpu_ram_cached": 7.046875,
-      "eval_gpu_ram_total": 39.56402587890625,
-      "eval_gpu_utilization": 30,
-      "eval_loss": 3.145473003387451,
-      "eval_precision": 0.23690476190476187,
-      "eval_recall": 0.3,
-      "eval_runtime": 0.2137,
-      "eval_samples_per_second": 93.578,
-      "eval_steps_per_second": 14.037,
-      "eval_system_ram_total": 83.48074722290039,
-      "eval_system_ram_used": 4.938743591308594,
-      "step": 300
-    }
-  ],
-  "max_steps": 500,
-  "num_train_epochs": 50,
-  "total_flos": 107663196007104.0,
-  "trial_name": null,
-  "trial_params": null
-}

checkpoint-330/added_tokens.json

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

checkpoint-330/config.json

@@ -1,59 +0,0 @@
-{
-  "_name_or_path": "microsoft/deberta-v3-base",
-  "architectures": [
-    "DebertaV2ForSequenceClassification"
-  ],
-  "attention_probs_dropout_prob": 0.1,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
-  "id2label": {
-    "0": "Society & Culture",
-    "1": "Science & Mathematics",
-    "2": "Health",
-    "3": "Education & Reference",
-    "4": "Computers & Internet",
-    "5": "Sports",
-    "6": "Business & Finance",
-    "7": "Entertainment & Music",
-    "8": "Family & Relationships",
-    "9": "Politics & Government"
-  },
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "label2id": {
-    "Business & Finance": 6,
-    "Computers & Internet": 4,
-    "Education & Reference": 3,
-    "Entertainment & Music": 7,
-    "Family & Relationships": 8,
-    "Health": 2,
-    "Politics & Government": 9,
-    "Science & Mathematics": 1,
-    "Society & Culture": 0,
-    "Sports": 5
-  },
-  "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": 12,
-  "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": "4.31.0",
-  "type_vocab_size": 0,
-  "vocab_size": 128100
-}

checkpoint-330/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ed024c714c4752b95f5020e1ffd2f59940ea99f2bac5826eb9ebfc11a6402ee0
-size 1475557125

checkpoint-330/special_tokens_map.json

@@ -1,9 +0,0 @@
-{
-  "bos_token": "[CLS]",
-  "cls_token": "[CLS]",
-  "eos_token": "[SEP]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
-}

checkpoint-330/spm.model

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

checkpoint-330/tokenizer_config.json

@@ -1,16 +0,0 @@
-{
-  "bos_token": "[CLS]",
-  "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_lower_case": false,
-  "eos_token": "[SEP]",
-  "mask_token": "[MASK]",
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "sp_model_kwargs": {},
-  "split_by_punct": false,
-  "tokenizer_class": "DebertaV2Tokenizer",
-  "unk_token": "[UNK]",
-  "vocab_type": "spm"
-}

{checkpoint-320 → checkpoint-500}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10d02ebf27d06e75305b818f564bc0d6388b260a305ac331618c2ddf0c12353a
+oid sha256:662b6c43d90b5b129e2b7b7713353e9f9889d3127c26a7f36cb0f988814a9a23
 size 1475557125

{checkpoint-330 → checkpoint-500}/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd18743bdfde8be92fbd991f5cad7d7c0cd7aaca0583e919148be21d96ce8668
+oid sha256:70ba09d349c8c8ac319ad8ae7821294c459961bd17df3092a1a44adff6bd6a8c
 size 737788917

{checkpoint-330 → checkpoint-500}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:172ad3783b50b89f49d659f4f234a7bb8ccb479b05073e534df5e40060af3c37
+oid sha256:c2d91aed1234e662896d21f942670a632f57a0e62c4b4b06ccfd49ae3369c96c
 size 14575

{checkpoint-330 → checkpoint-500}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfeff0174eed12f41b793614fed3bdc8efce764c415e04518a3297ac70a962f8
+oid sha256:d4eb82f131c89d4efc13f66a2d38e7dfbfa48833549604228e3e4ad7e42ffe0c
 size 627

{checkpoint-330 → checkpoint-500}/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 33.0,
-  "global_step": 330,
+  "epoch": 50.0,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -350,11 +350,193 @@
       "eval_system_ram_total": 83.48074722290039,
       "eval_system_ram_used": 4.919792175292969,
       "step": 325
+    },
+    {
+      "epoch": 35.0,
+      "learning_rate": 6.08e-06,
+      "loss": 0.0163,
+      "step": 350
+    },
+    {
+      "epoch": 35.0,
+      "eval_accuracy": 0.3,
+      "eval_disk_space_total": 78.1898422241211,
+      "eval_disk_space_used": 40.403133392333984,
+      "eval_f1": 0.23444444444444446,
+      "eval_gpu_ram_allocated": 4.8430633544921875,
+      "eval_gpu_ram_cached": 7.046875,
+      "eval_gpu_ram_total": 39.56402587890625,
+      "eval_gpu_utilization": 42,
+      "eval_loss": 3.3280787467956543,
+      "eval_precision": 0.2369047619047619,
+      "eval_recall": 0.3,
+      "eval_runtime": 0.2124,
+      "eval_samples_per_second": 94.164,
+      "eval_steps_per_second": 14.125,
+      "eval_system_ram_total": 83.48074722290039,
+      "eval_system_ram_used": 4.970893859863281,
+      "step": 350
+    },
+    {
+      "epoch": 37.5,
+      "learning_rate": 5.0800000000000005e-06,
+      "loss": 0.015,
+      "step": 375
+    },
+    {
+      "epoch": 37.5,
+      "eval_accuracy": 0.3,
+      "eval_disk_space_total": 78.1898422241211,
+      "eval_disk_space_used": 40.40315246582031,
+      "eval_f1": 0.23444444444444446,
+      "eval_gpu_ram_allocated": 4.843059062957764,
+      "eval_gpu_ram_cached": 7.046875,
+      "eval_gpu_ram_total": 39.56402587890625,
+      "eval_gpu_utilization": 41,
+      "eval_loss": 3.331848621368408,
+      "eval_precision": 0.23690476190476187,
+      "eval_recall": 0.3,
+      "eval_runtime": 0.2059,
+      "eval_samples_per_second": 97.115,
+      "eval_steps_per_second": 14.567,
+      "eval_system_ram_total": 83.48074722290039,
+      "eval_system_ram_used": 4.9642181396484375,
+      "step": 375
+    },
+    {
+      "epoch": 40.0,
+      "learning_rate": 4.08e-06,
+      "loss": 0.0133,
+      "step": 400
+    },
+    {
+      "epoch": 40.0,
+      "eval_accuracy": 0.3,
+      "eval_disk_space_total": 78.1898422241211,
+      "eval_disk_space_used": 40.40321350097656,
+      "eval_f1": 0.2511111111111112,
+      "eval_gpu_ram_allocated": 4.843057632446289,
+      "eval_gpu_ram_cached": 7.046875,
+      "eval_gpu_ram_total": 39.56402587890625,
+      "eval_gpu_utilization": 37,
+      "eval_loss": 3.361743927001953,
+      "eval_precision": 0.2869047619047619,
+      "eval_recall": 0.3,
+      "eval_runtime": 0.2122,
+      "eval_samples_per_second": 94.248,
+      "eval_steps_per_second": 14.137,
+      "eval_system_ram_total": 83.48074722290039,
+      "eval_system_ram_used": 4.96075439453125,
+      "step": 400
+    },
+    {
+      "epoch": 42.5,
+      "learning_rate": 3.08e-06,
+      "loss": 0.0127,
+      "step": 425
+    },
+    {
+      "epoch": 42.5,
+      "eval_accuracy": 0.3,
+      "eval_disk_space_total": 78.1898422241211,
+      "eval_disk_space_used": 40.403221130371094,
+      "eval_f1": 0.23444444444444446,
+      "eval_gpu_ram_allocated": 4.843057632446289,
+      "eval_gpu_ram_cached": 7.046875,
+      "eval_gpu_ram_total": 39.56402587890625,
+      "eval_gpu_utilization": 39,
+      "eval_loss": 3.3787875175476074,
+      "eval_precision": 0.23690476190476187,
+      "eval_recall": 0.3,
+      "eval_runtime": 0.2221,
+      "eval_samples_per_second": 90.039,
+      "eval_steps_per_second": 13.506,
+      "eval_system_ram_total": 83.48074722290039,
+      "eval_system_ram_used": 4.961738586425781,
+      "step": 425
+    },
+    {
+      "epoch": 45.0,
+      "learning_rate": 2.08e-06,
+      "loss": 0.0129,
+      "step": 450
+    },
+    {
+      "epoch": 45.0,
+      "eval_accuracy": 0.3,
+      "eval_disk_space_total": 78.1898422241211,
+      "eval_disk_space_used": 40.40324783325195,
+      "eval_f1": 0.2511111111111112,
+      "eval_gpu_ram_allocated": 4.843059062957764,
+      "eval_gpu_ram_cached": 7.046875,
+      "eval_gpu_ram_total": 39.56402587890625,
+      "eval_gpu_utilization": 41,
+      "eval_loss": 3.392756700515747,
+      "eval_precision": 0.2869047619047619,
+      "eval_recall": 0.3,
+      "eval_runtime": 0.2132,
+      "eval_samples_per_second": 93.819,
+      "eval_steps_per_second": 14.073,
+      "eval_system_ram_total": 83.48074722290039,
+      "eval_system_ram_used": 4.957637786865234,
+      "step": 450
+    },
+    {
+      "epoch": 47.5,
+      "learning_rate": 1.08e-06,
+      "loss": 0.0121,
+      "step": 475
+    },
+    {
+      "epoch": 47.5,
+      "eval_accuracy": 0.3,
+      "eval_disk_space_total": 78.1898422241211,
+      "eval_disk_space_used": 40.403297424316406,
+      "eval_f1": 0.23444444444444446,
+      "eval_gpu_ram_allocated": 4.8430633544921875,
+      "eval_gpu_ram_cached": 7.046875,
+      "eval_gpu_ram_total": 39.56402587890625,
+      "eval_gpu_utilization": 37,
+      "eval_loss": 3.389730453491211,
+      "eval_precision": 0.2369047619047619,
+      "eval_recall": 0.3,
+      "eval_runtime": 0.2122,
+      "eval_samples_per_second": 94.239,
+      "eval_steps_per_second": 14.136,
+      "eval_system_ram_total": 83.48074722290039,
+      "eval_system_ram_used": 4.942131042480469,
+      "step": 475
+    },
+    {
+      "epoch": 50.0,
+      "learning_rate": 8e-08,
+      "loss": 0.0124,
+      "step": 500
+    },
+    {
+      "epoch": 50.0,
+      "eval_accuracy": 0.3,
+      "eval_disk_space_total": 78.1898422241211,
+      "eval_disk_space_used": 40.4033203125,
+      "eval_f1": 0.23444444444444446,
+      "eval_gpu_ram_allocated": 4.843059062957764,
+      "eval_gpu_ram_cached": 7.046875,
+      "eval_gpu_ram_total": 39.56402587890625,
+      "eval_gpu_utilization": 38,
+      "eval_loss": 3.3983218669891357,
+      "eval_precision": 0.2369047619047619,
+      "eval_recall": 0.3,
+      "eval_runtime": 0.2214,
+      "eval_samples_per_second": 90.351,
+      "eval_steps_per_second": 13.553,
+      "eval_system_ram_total": 83.48074722290039,
+      "eval_system_ram_used": 4.958106994628906,
+      "step": 500
     }
   ],
   "max_steps": 500,
   "num_train_epochs": 50,
-  "total_flos": 111026386045056.0,
+  "total_flos": 168180059293920.0,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd18743bdfde8be92fbd991f5cad7d7c0cd7aaca0583e919148be21d96ce8668
+oid sha256:70ba09d349c8c8ac319ad8ae7821294c459961bd17df3092a1a44adff6bd6a8c
 size 737788917

runs/Jul22_22-00-48_9cc823f43576/events.out.tfevents.1690063253.9cc823f43576.282.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e999567e134d87b11c54fa290ab2e27a310e33b30d4b21ec4cb70c2181feb3b4
-size 19330
+oid sha256:31890ceef7ba0d7f63da813a8499776805624be35cb8f5759a0686848a9108d1
+size 27398

checkpoint-330/training_args.bin → runs/Jul22_22-00-48_9cc823f43576/events.out.tfevents.1690063714.9cc823f43576.282.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47900edd0b53679608a0ede66451399bbfa5cd566fbc3709079b0e0cd194e43b
-size 4091
+oid sha256:e4404bb0eef3ad97244fe6018ae250a8e464657a68b3198d21200bcaaa5e6db4
+size 1033