Training in progress, step 9000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:301efe15fcd22f178a59817e7ac95437175ae1902e5f8351d10927e9d460d888
+oid sha256:5dfabab5bf5157607fcc2602e95b9ce10a5b071f3b4fe4e130b9741ece0fba0a
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da312327cdcf8ee87d3ec3f29034a334cec0891a627a2192c1ab49ddbc3560d9
+oid sha256:0adc8bbd6eae86e2c260d1fab52c374eee35d382f517b5c8cbd8551e8f7a77a3
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fe1606aea4247336928fb0ca7460d9c32bfd4a5f09cd12bbfa040c328a1e6f1
+oid sha256:d89768c598d4fd9b0ed22710bf5b3c13eec14bfaad44bcf482c9b7c5838dd420
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f1cf6f72829f199e2c33545d808f1bb98dc287a37068472d85b2db721614981
+oid sha256:620c7bc458bafe9b83f6fadd9f5a5700bbd89b438e325546819b47236eeb8e3e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.08401757478713989,
-  "best_model_checkpoint": "./fine-tuned/checkpoint-8000",
-  "epoch": 0.68,
+  "best_metric": 0.0838891863822937,
+  "best_model_checkpoint": "./fine-tuned/checkpoint-9000",
+  "epoch": 0.72,
   "eval_steps": 500,
-  "global_step": 8500,
+  "global_step": 9000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1333,6 +1333,84 @@
       "eval_samples_per_second": 22.712,
       "eval_steps_per_second": 5.678,
       "step": 8500
+    },
+    {
+      "epoch": 0.684,
+      "grad_norm": 0.113871268928051,
+      "learning_rate": 1.97424e-05,
+      "loss": 0.0651,
+      "step": 8550
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 0.12488531321287155,
+      "learning_rate": 1.96824e-05,
+      "loss": 0.0624,
+      "step": 8600
+    },
+    {
+      "epoch": 0.692,
+      "grad_norm": 0.16593888401985168,
+      "learning_rate": 1.96224e-05,
+      "loss": 0.0619,
+      "step": 8650
+    },
+    {
+      "epoch": 0.696,
+      "grad_norm": 0.14381399750709534,
+      "learning_rate": 1.95624e-05,
+      "loss": 0.0631,
+      "step": 8700
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.19177569448947906,
+      "learning_rate": 1.95024e-05,
+      "loss": 0.0584,
+      "step": 8750
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.18918590247631073,
+      "learning_rate": 1.94424e-05,
+      "loss": 0.0563,
+      "step": 8800
+    },
+    {
+      "epoch": 0.708,
+      "grad_norm": 0.1318553388118744,
+      "learning_rate": 1.93824e-05,
+      "loss": 0.0644,
+      "step": 8850
+    },
+    {
+      "epoch": 0.712,
+      "grad_norm": 0.11326153576374054,
+      "learning_rate": 1.93224e-05,
+      "loss": 0.0678,
+      "step": 8900
+    },
+    {
+      "epoch": 0.716,
+      "grad_norm": 0.1167350560426712,
+      "learning_rate": 1.92624e-05,
+      "loss": 0.0558,
+      "step": 8950
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.10959301143884659,
+      "learning_rate": 1.92024e-05,
+      "loss": 0.0618,
+      "step": 9000
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 0.0838891863822937,
+      "eval_runtime": 88.0828,
+      "eval_samples_per_second": 22.706,
+      "eval_steps_per_second": 5.676,
+      "step": 9000
     }
   ],
   "logging_steps": 50,
@@ -1352,7 +1430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.070456827904e+16,
+  "total_flos": 2.192248406016e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null