Upload folder using huggingface_hub

README.md

@@ -20,7 +20,8 @@ First BERT-style model trained from scratch on Sindhi text.
 | S1 | 500K lines  | 5 | 78.10 | from scratch |
 | S2 | 1.5M lines  | 3 | 41.62 | continued |
 | S3 | 1.49M lines | 2 | 28.46 | bf16, cosine LR |
-| S4 | 87M words   | 3 | 35.42 | grouped context |
+| S4 | 87M words   | 3 | 35.16 | grouped context, MLM=0.20 |
+| S5 | 87M words   | 2 | 29.45 | fine polish, MLM=0.15 |
 
 ## Usage
 

checkpoint-1962/config.json

@@ -0,0 +1,28 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "type_vocab_size": 1,
+  "use_cache": false,
+  "vocab_size": 32001
+}

checkpoint-1962/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b408867c203ef5560d1d08d8c10f23eb9ec84b0c35800910f671bbbbc54f310
+size 442633860

checkpoint-1962/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94b7e14d685848516c9ccb2ef50864ae9c59c5ddd1fdcade33822f46bb2f6140
+size 885391563

checkpoint-1962/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:533785fa47d37d3c80b2d9c2a504e57c9142557c2ae85831a5276a2fd23d116b
+size 14645

checkpoint-1962/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c1c18f6958e463b9bf1adf762c04149cbe5a397f12a80ca8aa0df8208fb9090
+size 1465

checkpoint-1962/trainer_state.json

@@ -0,0 +1,184 @@
+{
+  "best_global_step": 1962,
+  "best_metric": 3.396049737930298,
+  "best_model_checkpoint": "sindhibert_session5/checkpoint-1962",
+  "epoch": 1.0,
+  "eval_steps": 1962,
+  "global_step": 1962,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05098139179199592,
+      "grad_norm": 5.245308876037598,
+      "learning_rate": 2.1063829787234044e-06,
+      "loss": 14.123677978515625,
+      "step": 100
+    },
+    {
+      "epoch": 0.10196278358399184,
+      "grad_norm": 5.646098613739014,
+      "learning_rate": 4.23404255319149e-06,
+      "loss": 14.066470947265625,
+      "step": 200
+    },
+    {
+      "epoch": 0.15294417537598776,
+      "grad_norm": 5.477426528930664,
+      "learning_rate": 4.99628768445363e-06,
+      "loss": 14.01585693359375,
+      "step": 300
+    },
+    {
+      "epoch": 0.20392556716798368,
+      "grad_norm": 5.2961344718933105,
+      "learning_rate": 4.975657001043815e-06,
+      "loss": 13.965966796875,
+      "step": 400
+    },
+    {
+      "epoch": 0.2549069589599796,
+      "grad_norm": 5.533503532409668,
+      "learning_rate": 4.937082682936824e-06,
+      "loss": 13.97388671875,
+      "step": 500
+    },
+    {
+      "epoch": 0.3058883507519755,
+      "grad_norm": 5.314619064331055,
+      "learning_rate": 4.8808443179239025e-06,
+      "loss": 13.95988525390625,
+      "step": 600
+    },
+    {
+      "epoch": 0.35686974254397147,
+      "grad_norm": 5.3324384689331055,
+      "learning_rate": 4.807349523327375e-06,
+      "loss": 13.953388671875,
+      "step": 700
+    },
+    {
+      "epoch": 0.40785113433596737,
+      "grad_norm": 5.467737674713135,
+      "learning_rate": 4.717130991578312e-06,
+      "loss": 13.9411962890625,
+      "step": 800
+    },
+    {
+      "epoch": 0.45883252612796327,
+      "grad_norm": 5.45510721206665,
+      "learning_rate": 4.610842629246138e-06,
+      "loss": 13.934332275390625,
+      "step": 900
+    },
+    {
+      "epoch": 0.5098139179199592,
+      "grad_norm": 5.6341962814331055,
+      "learning_rate": 4.489254817504595e-06,
+      "loss": 13.926766357421876,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5607953097119551,
+      "grad_norm": 5.584266662597656,
+      "learning_rate": 4.353248828386359e-06,
+      "loss": 13.91165283203125,
+      "step": 1100
+    },
+    {
+      "epoch": 0.611776701503951,
+      "grad_norm": 5.35775899887085,
+      "learning_rate": 4.203810437297447e-06,
+      "loss": 13.915504150390625,
+      "step": 1200
+    },
+    {
+      "epoch": 0.6627580932959469,
+      "grad_norm": 5.549437999725342,
+      "learning_rate": 4.042022778088111e-06,
+      "loss": 13.945462646484375,
+      "step": 1300
+    },
+    {
+      "epoch": 0.7137394850879429,
+      "grad_norm": 5.455720901489258,
+      "learning_rate": 3.869058492466847e-06,
+      "loss": 13.89906494140625,
+      "step": 1400
+    },
+    {
+      "epoch": 0.7647208768799388,
+      "grad_norm": 5.856232166290283,
+      "learning_rate": 3.6861712306588434e-06,
+      "loss": 13.905211181640626,
+      "step": 1500
+    },
+    {
+      "epoch": 0.8157022686719347,
+      "grad_norm": 5.481319904327393,
+      "learning_rate": 3.4946865649123025e-06,
+      "loss": 13.896219482421875,
+      "step": 1600
+    },
+    {
+      "epoch": 0.8666836604639306,
+      "grad_norm": 5.278250217437744,
+      "learning_rate": 3.2959923817118296e-06,
+      "loss": 13.906019287109375,
+      "step": 1700
+    },
+    {
+      "epoch": 0.9176650522559265,
+      "grad_norm": 5.768893718719482,
+      "learning_rate": 3.091528822336405e-06,
+      "loss": 13.93161376953125,
+      "step": 1800
+    },
+    {
+      "epoch": 0.9686464440479226,
+      "grad_norm": 5.366046905517578,
+      "learning_rate": 2.8827778446730764e-06,
+      "loss": 13.906478271484374,
+      "step": 1900
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.396049737930298,
+      "eval_runtime": 7.952,
+      "eval_samples_per_second": 637.827,
+      "eval_steps_per_second": 10.06,
+      "step": 1962
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 3924,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 1962,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.321661037009623e+17,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1962/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0a0f3ce1e27fd1d47d30a38c39aa86503e7f6fb63f533cef4d2e9ac2db41014
+size 5137

checkpoint-3924/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66c9b40b4d1b2943a622be928e3f8beb231f2cf80d2acbe19352c740edfa76b9
+oid sha256:9f0ec985a6dec33fba0018d1ffbc1fcc4317a2291a75a8d6fc24f269454e6581
 size 442633860

checkpoint-3924/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cdbb31b8e427b2d5c5d5dce127c362cb391d70f8282995b2a405651b6695774
+oid sha256:6ed56030f6a04a8bb3427806cc07b51579a5943f3c41ece7a44ff4210b13a4a7
 size 885391563

checkpoint-3924/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8eef8b1a8fe3ca13b13452c68d049d5772a114b25d47fd7c271209bdd37c174b
+oid sha256:e6f67f71bb87604f1d79bd9533843f4244e3f1cc9c56bc98e0df5eacc07beced
 size 1465

checkpoint-3924/trainer_state.json

@@ -1,7 +1,7 @@
 {
   "best_global_step": 3924,
-  "best_metric": 3.56946063041687,
-  "best_model_checkpoint": "sindhibert_session4/checkpoint-3924",
+  "best_metric": 3.390385389328003,
+  "best_model_checkpoint": "sindhibert_session5/checkpoint-3924",
   "epoch": 2.0,
   "eval_steps": 1962,
   "global_step": 3924,
@@ -11,298 +11,298 @@
   "log_history": [
     {
       "epoch": 0.05098139179199592,
-      "grad_norm": 4.590001106262207,
-      "learning_rate": 5.609065155807366e-06,
-      "loss": 15.86372314453125,
+      "grad_norm": 5.245308876037598,
+      "learning_rate": 2.1063829787234044e-06,
+      "loss": 14.123677978515625,
       "step": 100
     },
     {
       "epoch": 0.10196278358399184,
-      "grad_norm": 5.000253677368164,
-      "learning_rate": 1.1274787535410765e-05,
-      "loss": 15.6683056640625,
+      "grad_norm": 5.646098613739014,
+      "learning_rate": 4.23404255319149e-06,
+      "loss": 14.066470947265625,
       "step": 200
     },
     {
       "epoch": 0.15294417537598776,
-      "grad_norm": 5.164661407470703,
-      "learning_rate": 1.6940509915014164e-05,
-      "loss": 15.58547607421875,
+      "grad_norm": 5.477426528930664,
+      "learning_rate": 4.99628768445363e-06,
+      "loss": 14.01585693359375,
       "step": 300
     },
     {
       "epoch": 0.20392556716798368,
-      "grad_norm": 4.895200729370117,
-      "learning_rate": 1.999658933249201e-05,
-      "loss": 15.5261376953125,
+      "grad_norm": 5.2961344718933105,
+      "learning_rate": 4.975657001043815e-06,
+      "loss": 13.965966796875,
       "step": 400
     },
     {
       "epoch": 0.2549069589599796,
-      "grad_norm": 5.010247707366943,
-      "learning_rate": 1.9965659596003744e-05,
-      "loss": 15.493291015625,
+      "grad_norm": 5.533503532409668,
+      "learning_rate": 4.937082682936824e-06,
+      "loss": 13.97388671875,
       "step": 500
     },
     {
       "epoch": 0.3058883507519755,
-      "grad_norm": 4.85853910446167,
-      "learning_rate": 1.990261043359342e-05,
-      "loss": 15.43971435546875,
+      "grad_norm": 5.314619064331055,
+      "learning_rate": 4.8808443179239025e-06,
+      "loss": 13.95988525390625,
       "step": 600
     },
     {
       "epoch": 0.35686974254397147,
-      "grad_norm": 4.788653373718262,
-      "learning_rate": 1.9807645053376055e-05,
-      "loss": 15.409666748046876,
+      "grad_norm": 5.3324384689331055,
+      "learning_rate": 4.807349523327375e-06,
+      "loss": 13.953388671875,
       "step": 700
     },
     {
       "epoch": 0.40785113433596737,
-      "grad_norm": 4.742185592651367,
-      "learning_rate": 1.968106952977309e-05,
-      "loss": 15.346304931640624,
+      "grad_norm": 5.467737674713135,
+      "learning_rate": 4.717130991578312e-06,
+      "loss": 13.9411962890625,
       "step": 800
     },
     {
       "epoch": 0.45883252612796327,
-      "grad_norm": 4.758422374725342,
-      "learning_rate": 1.9523291817031276e-05,
-      "loss": 15.344024658203125,
+      "grad_norm": 5.45510721206665,
+      "learning_rate": 4.610842629246138e-06,
+      "loss": 13.934332275390625,
       "step": 900
     },
     {
       "epoch": 0.5098139179199592,
-      "grad_norm": 4.854381084442139,
-      "learning_rate": 1.933482043438185e-05,
-      "loss": 15.307811279296875,
+      "grad_norm": 5.6341962814331055,
+      "learning_rate": 4.489254817504595e-06,
+      "loss": 13.926766357421876,
       "step": 1000
     },
     {
       "epoch": 0.5607953097119551,
-      "grad_norm": 4.7934041023254395,
-      "learning_rate": 1.9116262827077703e-05,
-      "loss": 15.254422607421875,
+      "grad_norm": 5.584266662597656,
+      "learning_rate": 4.353248828386359e-06,
+      "loss": 13.91165283203125,
       "step": 1100
     },
     {
       "epoch": 0.611776701503951,
-      "grad_norm": 4.670731544494629,
-      "learning_rate": 1.88683234085909e-05,
-      "loss": 15.23345703125,
+      "grad_norm": 5.35775899887085,
+      "learning_rate": 4.203810437297447e-06,
+      "loss": 13.915504150390625,
       "step": 1200
     },
     {
       "epoch": 0.6627580932959469,
-      "grad_norm": 4.993561267852783,
-      "learning_rate": 1.8591801290280664e-05,
-      "loss": 15.2450927734375,
+      "grad_norm": 5.549437999725342,
+      "learning_rate": 4.042022778088111e-06,
+      "loss": 13.945462646484375,
       "step": 1300
     },
     {
       "epoch": 0.7137394850879429,
-      "grad_norm": 4.720964431762695,
-      "learning_rate": 1.8287587705849013e-05,
-      "loss": 15.1839599609375,
+      "grad_norm": 5.455720901489258,
+      "learning_rate": 3.869058492466847e-06,
+      "loss": 13.89906494140625,
       "step": 1400
     },
     {
       "epoch": 0.7647208768799388,
-      "grad_norm": 5.050419330596924,
-      "learning_rate": 1.7956663138885173e-05,
-      "loss": 15.164833984375,
+      "grad_norm": 5.856232166290283,
+      "learning_rate": 3.6861712306588434e-06,
+      "loss": 13.905211181640626,
       "step": 1500
     },
     {
       "epoch": 0.8157022686719347,
-      "grad_norm": 4.826648712158203,
-      "learning_rate": 1.760009416275661e-05,
-      "loss": 15.130496826171875,
+      "grad_norm": 5.481319904327393,
+      "learning_rate": 3.4946865649123025e-06,
+      "loss": 13.896219482421875,
       "step": 1600
     },
     {
       "epoch": 0.8666836604639306,
-      "grad_norm": 4.858438014984131,
-      "learning_rate": 1.721903000303185e-05,
-      "loss": 15.125797119140625,
+      "grad_norm": 5.278250217437744,
+      "learning_rate": 3.2959923817118296e-06,
+      "loss": 13.906019287109375,
       "step": 1700
     },
     {
       "epoch": 0.9176650522559265,
-      "grad_norm": 4.9611430168151855,
-      "learning_rate": 1.6814698833514326e-05,
-      "loss": 15.13617431640625,
+      "grad_norm": 5.768893718719482,
+      "learning_rate": 3.091528822336405e-06,
+      "loss": 13.93161376953125,
       "step": 1800
     },
     {
       "epoch": 0.9686464440479226,
-      "grad_norm": 4.663859844207764,
-      "learning_rate": 1.63884038178253e-05,
-      "loss": 15.072591552734375,
+      "grad_norm": 5.366046905517578,
+      "learning_rate": 2.8827778446730764e-06,
+      "loss": 13.906478271484374,
       "step": 1900
     },
     {
       "epoch": 1.0,
-      "eval_loss": 3.636704444885254,
-      "eval_runtime": 8.0138,
-      "eval_samples_per_second": 632.91,
-      "eval_steps_per_second": 9.983,
+      "eval_loss": 3.396049737930298,
+      "eval_runtime": 7.952,
+      "eval_samples_per_second": 637.827,
+      "eval_steps_per_second": 10.06,
       "step": 1962
     },
     {
       "epoch": 1.0193729288809585,
-      "grad_norm": 4.863068103790283,
-      "learning_rate": 1.5941518909293737e-05,
-      "loss": 14.968798828125,
+      "grad_norm": 5.584351062774658,
+      "learning_rate": 2.6712524819426355e-06,
+      "loss": 13.823892822265625,
       "step": 2000
     },
     {
       "epoch": 1.0703543206729544,
-      "grad_norm": 5.036495685577393,
-      "learning_rate": 1.5475484422690282e-05,
-      "loss": 15.0290869140625,
+      "grad_norm": 5.338160037994385,
+      "learning_rate": 2.458485876190375e-06,
+      "loss": 13.90267333984375,
       "step": 2100
     },
     {
       "epoch": 1.1213357124649503,
-      "grad_norm": 5.248174667358398,
-      "learning_rate": 1.4991802392077543e-05,
-      "loss": 15.004036865234376,
+      "grad_norm": 5.378915309906006,
+      "learning_rate": 2.246020166027488e-06,
+      "loss": 13.9045458984375,
       "step": 2200
     },
     {
       "epoch": 1.1723171042569462,
-      "grad_norm": 4.950564384460449,
-      "learning_rate": 1.4492031729738489e-05,
-      "loss": 15.002611083984375,
+      "grad_norm": 5.420534133911133,
+      "learning_rate": 2.0353953091650912e-06,
+      "loss": 13.91886474609375,
       "step": 2300
     },
     {
       "epoch": 1.2232984960489421,
-      "grad_norm": 4.509192943572998,
-      "learning_rate": 1.3977783201785732e-05,
-      "loss": 14.96060302734375,
+      "grad_norm": 5.299575328826904,
+      "learning_rate": 1.82813792075548e-06,
+      "loss": 13.879603271484376,
       "step": 2400
     },
     {
       "epoch": 1.274279887840938,
-      "grad_norm": 4.900182723999023,
-      "learning_rate": 1.3450714236645352e-05,
-      "loss": 14.971297607421874,
+      "grad_norm": 5.256579875946045,
+      "learning_rate": 1.6257502084406458e-06,
+      "loss": 13.92048828125,
       "step": 2500
     },
     {
       "epoch": 1.325261279632934,
-      "grad_norm": 5.138764381408691,
-      "learning_rate": 1.2912523583147625e-05,
-      "loss": 14.928385009765625,
+      "grad_norm": 5.846710205078125,
+      "learning_rate": 1.4296990843071351e-06,
+      "loss": 13.912366943359375,
       "step": 2600
     },
     {
       "epoch": 1.3762426714249298,
-      "grad_norm": 4.894199848175049,
-      "learning_rate": 1.2364945835441636e-05,
-      "loss": 14.938167724609375,
+      "grad_norm": 5.547558307647705,
+      "learning_rate": 1.2414055326641378e-06,
+      "loss": 13.929051513671874,
       "step": 2700
     },
     {
       "epoch": 1.4272240632169257,
-      "grad_norm": 4.8737921714782715,
-      "learning_rate": 1.1809745842380042e-05,
-      "loss": 14.923902587890625,
+      "grad_norm": 5.693734169006348,
+      "learning_rate": 1.062234310707458e-06,
+      "loss": 13.929571533203125,
       "step": 2800
     },
     {
       "epoch": 1.4782054550089216,
-      "grad_norm": 4.8258819580078125,
-      "learning_rate": 1.1248713019392635e-05,
-      "loss": 14.89677001953125,
+      "grad_norm": 5.414492607116699,
+      "learning_rate": 8.934840567192496e-07,
+      "loss": 13.91981201171875,
       "step": 2900
     },
     {
       "epoch": 1.5291868468009175,
-      "grad_norm": 4.769787788391113,
-      "learning_rate": 1.0683655581181524e-05,
-      "loss": 14.87692626953125,
+      "grad_norm": 5.501009941101074,
+      "learning_rate": 7.363778774995834e-07,
+      "loss": 13.91615478515625,
       "step": 3000
     },
     {
       "epoch": 1.5801682385929134,
-      "grad_norm": 4.92316198348999,
-      "learning_rate": 1.0116394713826117e-05,
-      "loss": 14.849693603515625,
+      "grad_norm": 5.355737686157227,
+      "learning_rate": 5.920544832524166e-07,
+      "loss": 13.9007421875,
       "step": 3100
     },
     {
       "epoch": 1.6311496303849093,
-      "grad_norm": 4.873258590698242,
-      "learning_rate": 9.548758705081177e-06,
-      "loss": 14.833634033203126,
+      "grad_norm": 5.376833915710449,
+      "learning_rate": 4.61559934180571e-07,
+      "loss": 13.915396728515624,
       "step": 3200
     },
     {
       "epoch": 1.6821310221769055,
-      "grad_norm": 4.738825798034668,
-      "learning_rate": 8.98257705178612e-06,
-      "loss": 14.85665283203125,
+      "grad_norm": 5.302165985107422,
+      "learning_rate": 3.4584005861063974e-07,
+      "loss": 13.94998046875,
       "step": 3300
     },
     {
       "epoch": 1.7331124139689014,
-      "grad_norm": 4.907736778259277,
-      "learning_rate": 8.419674563377416e-06,
-      "loss": 14.8664599609375,
+      "grad_norm": 5.571377277374268,
+      "learning_rate": 2.4573359760148354e-07,
+      "loss": 13.98015380859375,
       "step": 3400
     },
     {
       "epoch": 1.7840938057608973,
-      "grad_norm": 4.977413177490234,
-      "learning_rate": 7.861865480508541e-06,
-      "loss": 14.83008056640625,
+      "grad_norm": 5.618070125579834,
+      "learning_rate": 1.619661257243843e-07,
+      "loss": 13.96041015625,
       "step": 3500
     },
     {
       "epoch": 1.8350751975528932,
-      "grad_norm": 4.792273044586182,
-      "learning_rate": 7.310947627733231e-06,
-      "loss": 14.81404541015625,
+      "grad_norm": 5.216390132904053,
+      "learning_rate": 9.514479207723276e-08,
+      "loss": 13.9774560546875,
       "step": 3600
     },
     {
       "epoch": 1.886056589344889,
-      "grad_norm": 4.84648323059082,
-      "learning_rate": 6.768696619097996e-06,
-      "loss": 14.831793212890625,
+      "grad_norm": 5.458727836608887,
+      "learning_rate": 4.575391965002174e-08,
+      "loss": 14.00027587890625,
       "step": 3700
     },
     {
       "epoch": 1.9370379811368852,
-      "grad_norm": 4.854404449462891,
-      "learning_rate": 6.236860135319321e-06,
-      "loss": 14.826976318359375,
+      "grad_norm": 5.513509273529053,
+      "learning_rate": 1.4151494937582056e-08,
+      "loss": 14.0021728515625,
       "step": 3800
     },
     {
       "epoch": 1.988019372928881,
-      "grad_norm": 4.615888595581055,
-      "learning_rate": 5.717152290990302e-06,
-      "loss": 14.767562255859374,
+      "grad_norm": 5.200069904327393,
+      "learning_rate": 5.665732429496751e-10,
+      "loss": 13.960343017578126,
       "step": 3900
     },
     {
       "epoch": 2.0,
-      "eval_loss": 3.56946063041687,
-      "eval_runtime": 8.0481,
-      "eval_samples_per_second": 630.208,
-      "eval_steps_per_second": 9.94,
+      "eval_loss": 3.390385389328003,
+      "eval_runtime": 7.9843,
+      "eval_samples_per_second": 635.249,
+      "eval_steps_per_second": 10.02,
       "step": 3924
     }
   ],
   "logging_steps": 100,
-  "max_steps": 5886,
+  "max_steps": 3924,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 2,
   "save_steps": 1962,
   "stateful_callbacks": {
     "EarlyStoppingCallback": {
@@ -320,7 +320,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }

checkpoint-3924/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:accc825ca2e280888c9eed825fcb7985700c1fb466ed8b16208ff9e7b14f1318
+oid sha256:a0a0f3ce1e27fd1d47d30a38c39aa86503e7f6fb63f533cef4d2e9ac2db41014
 size 5137

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:170894fbff2599922589dc645dfc871455543fe1f1fa33d3381f8353cf0b2a5b
+oid sha256:9f0ec985a6dec33fba0018d1ffbc1fcc4317a2291a75a8d6fc24f269454e6581
 size 442633860

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:accc825ca2e280888c9eed825fcb7985700c1fb466ed8b16208ff9e7b14f1318
+oid sha256:a0a0f3ce1e27fd1d47d30a38c39aa86503e7f6fb63f533cef4d2e9ac2db41014
 size 5137