Training in progress, step 12500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12d89b6cfeb0fa2a639fb1d022803e910e636a1653929f3379ba8ecc07936d2d
+oid sha256:84809acf96301d8b75572b9aa608e1f2afc0533f5ee30f46a0431492a1a275f4
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16e8ca890c29387dcb94fe4fee166151a4647fb651f909dbd97850a259675cfe
+oid sha256:984c2e60f40d6b8ecdf43a9a9b2fa6e7fed8a14485e9250dde4344fd78072844
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8eee71f4c759651379c503d3028bec932d355f171dd7453ec6f5c469e966f747
+oid sha256:96d212c2076c947a58295d88ed7a741f064eeda3b1a76832bac43470f08461ef
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b63e11db1a8e7c7a242100e7b3a9500ec8f1ad290a19c61a227cd5ed6d79dcc2
+oid sha256:cb61de87e596461b3a2fd8b9e3ff4ac6a0ba9feb11b3f41b64bad2f67194d86a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.10353059321641922,
-  "best_model_checkpoint": "./fine-tuned/checkpoint-12000",
-  "epoch": 2.107666637393519,
+  "best_metric": 0.10325244069099426,
+  "best_model_checkpoint": "./fine-tuned/checkpoint-12500",
+  "epoch": 2.195486080618249,
   "eval_steps": 100,
-  "global_step": 12000,
+  "global_step": 12500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2647,6 +2647,116 @@
       "eval_samples_per_second": 25.43,
       "eval_steps_per_second": 3.182,
       "step": 12000
+    },
+    {
+      "epoch": 2.116448581715992,
+      "grad_norm": 10527.5751953125,
+      "learning_rate": 1.4125241524679432e-05,
+      "loss": 0.0997,
+      "step": 12050
+    },
+    {
+      "epoch": 2.125230526038465,
+      "grad_norm": 12505.5380859375,
+      "learning_rate": 1.4059371157561918e-05,
+      "loss": 0.0981,
+      "step": 12100
+    },
+    {
+      "epoch": 2.125230526038465,
+      "eval_loss": 0.10333307832479477,
+      "eval_runtime": 175.2906,
+      "eval_samples_per_second": 25.443,
+      "eval_steps_per_second": 3.183,
+      "step": 12100
+    },
+    {
+      "epoch": 2.134012470360938,
+      "grad_norm": 9851.1923828125,
+      "learning_rate": 1.3993500790444406e-05,
+      "loss": 0.1006,
+      "step": 12150
+    },
+    {
+      "epoch": 2.142794414683411,
+      "grad_norm": 9354.9697265625,
+      "learning_rate": 1.3927630423326893e-05,
+      "loss": 0.1032,
+      "step": 12200
+    },
+    {
+      "epoch": 2.142794414683411,
+      "eval_loss": 0.10333764553070068,
+      "eval_runtime": 175.147,
+      "eval_samples_per_second": 25.464,
+      "eval_steps_per_second": 3.186,
+      "step": 12200
+    },
+    {
+      "epoch": 2.151576359005884,
+      "grad_norm": 7880.865234375,
+      "learning_rate": 1.3861760056209381e-05,
+      "loss": 0.0957,
+      "step": 12250
+    },
+    {
+      "epoch": 2.160358303328357,
+      "grad_norm": 17636.8515625,
+      "learning_rate": 1.3795889689091866e-05,
+      "loss": 0.0952,
+      "step": 12300
+    },
+    {
+      "epoch": 2.160358303328357,
+      "eval_loss": 0.10335990786552429,
+      "eval_runtime": 175.3211,
+      "eval_samples_per_second": 25.439,
+      "eval_steps_per_second": 3.183,
+      "step": 12300
+    },
+    {
+      "epoch": 2.1691402476508297,
+      "grad_norm": 15586.3701171875,
+      "learning_rate": 1.3730019321974355e-05,
+      "loss": 0.098,
+      "step": 12350
+    },
+    {
+      "epoch": 2.1779221919733027,
+      "grad_norm": 11448.01953125,
+      "learning_rate": 1.3664148954856841e-05,
+      "loss": 0.0942,
+      "step": 12400
+    },
+    {
+      "epoch": 2.1779221919733027,
+      "eval_loss": 0.10320650041103363,
+      "eval_runtime": 175.2718,
+      "eval_samples_per_second": 25.446,
+      "eval_steps_per_second": 3.184,
+      "step": 12400
+    },
+    {
+      "epoch": 2.1867041362957758,
+      "grad_norm": 13402.5732421875,
+      "learning_rate": 1.359827858773933e-05,
+      "loss": 0.1016,
+      "step": 12450
+    },
+    {
+      "epoch": 2.195486080618249,
+      "grad_norm": 7308.1123046875,
+      "learning_rate": 1.3532408220621816e-05,
+      "loss": 0.0978,
+      "step": 12500
+    },
+    {
+      "epoch": 2.195486080618249,
+      "eval_loss": 0.10325244069099426,
+      "eval_runtime": 175.4131,
+      "eval_samples_per_second": 25.426,
+      "eval_steps_per_second": 3.181,
+      "step": 12500
     }
   ],
   "logging_steps": 50,
@@ -2666,7 +2776,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.845569478852608e+16,
+  "total_flos": 6.089152635076608e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null