Training in progress, step 100, checkpoint

last-checkpoint/config.json

@@ -23,7 +23,7 @@
   "position_embedding_type": "rotary",
   "token_dropout": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.36.1",
+  "transformers_version": "4.45.2",
   "use_cache": true,
   "vocab_list": null,
   "vocab_size": 33

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:517b7a2aaaea838cb419a14f1b515d8b5cf1ed9fde5bf86d6fb0c135a3fcfda0
+oid sha256:3cd9a570af82105305cf26766d7851aa7b4e32c4acb1dcdebd64cd9be4301098
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ee99e2558f0635b821e5f0474f85cc00393edabfccf6bb4110621fc826ded64
+oid sha256:1eda6ad8e7e768db6abb9e04b52a008b2ecbe0f771c73b2c2ef7955c8d156e46
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee83cb0b382b6f7013b8e905a6b67eda9661bf7137607a26a8510616916ff33d
-size 14512
+oid sha256:6ad6436ce5e8229a5c4ab20ebe8cb7f55bf37abeb42cc6031740224925ccece0
+size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cf5a1d1bb94d2ab14807987fb6e7f78b0a603abb98dc702e91c99346c1c8745
-size 14512
+oid sha256:30ce71d1ff265e905b2803194965013784a4a1c2ebcd76de912d912dd5430327
+size 15024

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac4ea73b7e3e12f80c898b525181786b56f8cafbf02cf3e2661eb5c2237f1786
+size 15024

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df5ac7dd4844d948bc63bc160ee8e329c029b596511f3d1234b31a48caf5cc47
+size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0943229aeeb46312acb472f3efe5d902161c82efbe50119969078cb1567edce6
+oid sha256:cf0d25366e7e2e728cd627802a5543527b6178cf70866baa22ea5a7d28baa2af
 size 1064

last-checkpoint/trainer_state.json

@@ -1,35 +1,57 @@
 {
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 0.12421588721197441,
-  "eval_steps": 500,
-  "global_step": 500,
+  "best_metric": 1.1609667539596558,
+  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-100",
+  "epoch": 0.13386880856760375,
+  "eval_steps": 100,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.12,
-      "learning_rate": 9.958592132505176e-05,
-      "loss": 1.3838,
-      "step": 500
+      "epoch": 0.13386880856760375,
+      "grad_norm": 0.18324387073516846,
+      "learning_rate": 0.0009866131191432397,
+      "loss": 1.432,
+      "step": 100
     },
     {
-      "epoch": 0.12,
-      "eval_loss": 1.3269665241241455,
-      "eval_runtime": 63.2116,
-      "eval_samples_per_second": 255.634,
-      "eval_steps_per_second": 15.978,
-      "step": 500
+      "epoch": 0.13386880856760375,
+      "eval_loss": 1.1609667539596558,
+      "eval_runtime": 6.3619,
+      "eval_samples_per_second": 894.697,
+      "eval_steps_per_second": 3.615,
+      "step": 100
     }
   ],
-  "logging_steps": 500,
-  "max_steps": 120750,
+  "logging_steps": 100,
+  "max_steps": 7470,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 30,
-  "save_steps": 500,
-  "total_flos": 5001938240274432.0,
-  "train_batch_size": 8,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "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": 3631227076608000.0,
+  "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d5da2bb0b25e23c2716dc60237e84cea2973b9882dcc6ff60ec43fea4464a78
-size 4728
+oid sha256:6a3c35d00b3a9f09f09bbbd95adfdc6deaf5070563e785852debaae072505dcb
+size 5240