Training in progress, step 1500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a3f5e731113e9730efd9113f5f29cb905a8f1f2743b49cc72502432ddfbbe98
+oid sha256:c2de3e8a0e43fd8dd9c15b000eeb4f2021cdd5eccb54819b3b0728d1b7267178
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05b6c8071744fb730c3cce8cd6e59b3af98553013a5f6fbdbbd538f8a35c093e
+oid sha256:8b82ac85f6bf6ebbbd22442579d6ae1b2c1bf03a31bf32cacfc36ffd617eda63
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7412027fc58c1194bc8c7a74232f8612760d1fd20879b38d561f816aa317c25b
+oid sha256:2fae9953ba8f56f4659e95c4daffe7b5a7e29fdb6b98008ab375ed9889239ac9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34f558efbd4b52e03122b68bd1359b214dd840998b95d355abf0602295ddb8a5
+oid sha256:e08cecb96b0575af87573c227caf7ff2501936ebe822db040ebe990bb471ce73
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.09160277992486954,
-  "best_model_checkpoint": "./fine-tuned/checkpoint-1000",
-  "epoch": 0.08,
+  "best_metric": 0.09038107097148895,
+  "best_model_checkpoint": "./fine-tuned/checkpoint-1500",
+  "epoch": 0.12,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -163,6 +163,84 @@
       "eval_samples_per_second": 22.714,
       "eval_steps_per_second": 5.679,
       "step": 1000
+    },
+    {
+      "epoch": 0.084,
+      "grad_norm": 0.16729697585105896,
+      "learning_rate": 2.8741200000000002e-05,
+      "loss": 0.0823,
+      "step": 1050
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 0.14851506054401398,
+      "learning_rate": 2.86812e-05,
+      "loss": 0.0785,
+      "step": 1100
+    },
+    {
+      "epoch": 0.092,
+      "grad_norm": 0.22481797635555267,
+      "learning_rate": 2.86212e-05,
+      "loss": 0.0786,
+      "step": 1150
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.13808289170265198,
+      "learning_rate": 2.85612e-05,
+      "loss": 0.0785,
+      "step": 1200
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.17833128571510315,
+      "learning_rate": 2.85012e-05,
+      "loss": 0.0737,
+      "step": 1250
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 0.14926594495773315,
+      "learning_rate": 2.84412e-05,
+      "loss": 0.0767,
+      "step": 1300
+    },
+    {
+      "epoch": 0.108,
+      "grad_norm": 0.19346196949481964,
+      "learning_rate": 2.8381200000000002e-05,
+      "loss": 0.077,
+      "step": 1350
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 0.2675027847290039,
+      "learning_rate": 2.83212e-05,
+      "loss": 0.0806,
+      "step": 1400
+    },
+    {
+      "epoch": 0.116,
+      "grad_norm": 0.19048169255256653,
+      "learning_rate": 2.82612e-05,
+      "loss": 0.0756,
+      "step": 1450
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.1875162124633789,
+      "learning_rate": 2.82012e-05,
+      "loss": 0.0823,
+      "step": 1500
+    },
+    {
+      "epoch": 0.12,
+      "eval_loss": 0.09038107097148895,
+      "eval_runtime": 87.8777,
+      "eval_samples_per_second": 22.759,
+      "eval_steps_per_second": 5.69,
+      "step": 1500
     }
   ],
   "logging_steps": 50,
@@ -182,7 +260,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2435831562240000.0,
+  "total_flos": 3653747343360000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null