Training in progress, step 6000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69d1609aa46c5839ce2f0e40574d9fbde5dd0b26b3c6b24672dc874df7022413
+oid sha256:595cdcb5015115c6cbe2e6edbc30ee6705f67aa46b94c988f719a34cfbffd2cf
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3ba4184275341c1f83f8c7ea5cc044fa98a0d37f2482c3badd6c3656af1348b
+oid sha256:413d3093ca25037d97577232c37b28c1f8751cf177fef08c1cb404465db4cfd4
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98772bb230331f5cccf45e7b586be3da4127f0fa073760fa05315192ae7dcfa0
+oid sha256:6703b98a291d6e4043156fd5230a9d97acbef451284cebbec159795253cbebaf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2b96925e850cd8ef32abae6516af5134c66eaecf4e61ddbdb73aaa1b5b6a670
+oid sha256:f222e945c4954eb35a2a25c9f653bde2dc7b8763271375e010f0439b14074e8d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.08360794186592102,
-  "best_model_checkpoint": "./fine-tuned/checkpoint-5500",
-  "epoch": 0.88,
+  "best_metric": 0.08321517705917358,
+  "best_model_checkpoint": "./fine-tuned/checkpoint-6000",
+  "epoch": 0.96,
   "eval_steps": 500,
-  "global_step": 5500,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -865,6 +865,84 @@
       "eval_samples_per_second": 17.144,
       "eval_steps_per_second": 2.143,
       "step": 5500
+    },
+    {
+      "epoch": 0.888,
+      "grad_norm": 8200.35546875,
+      "learning_rate": 2.1119999999999998e-05,
+      "loss": 0.0676,
+      "step": 5550
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 8816.8076171875,
+      "learning_rate": 2.1040000000000002e-05,
+      "loss": 0.0626,
+      "step": 5600
+    },
+    {
+      "epoch": 0.904,
+      "grad_norm": 8886.630859375,
+      "learning_rate": 2.096e-05,
+      "loss": 0.0657,
+      "step": 5650
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": 8212.525390625,
+      "learning_rate": 2.088e-05,
+      "loss": 0.0619,
+      "step": 5700
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 5723.00439453125,
+      "learning_rate": 2.08e-05,
+      "loss": 0.0623,
+      "step": 5750
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 8616.3349609375,
+      "learning_rate": 2.072e-05,
+      "loss": 0.063,
+      "step": 5800
+    },
+    {
+      "epoch": 0.936,
+      "grad_norm": 7717.373046875,
+      "learning_rate": 2.064e-05,
+      "loss": 0.063,
+      "step": 5850
+    },
+    {
+      "epoch": 0.944,
+      "grad_norm": 6325.8193359375,
+      "learning_rate": 2.056e-05,
+      "loss": 0.0628,
+      "step": 5900
+    },
+    {
+      "epoch": 0.952,
+      "grad_norm": 6938.89111328125,
+      "learning_rate": 2.048e-05,
+      "loss": 0.0585,
+      "step": 5950
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 8704.166015625,
+      "learning_rate": 2.04e-05,
+      "loss": 0.0634,
+      "step": 6000
+    },
+    {
+      "epoch": 0.96,
+      "eval_loss": 0.08321517705917358,
+      "eval_runtime": 116.6701,
+      "eval_samples_per_second": 17.142,
+      "eval_steps_per_second": 2.143,
+      "step": 6000
     }
   ],
   "logging_steps": 50,
@@ -884,7 +962,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.679414718464e+16,
+  "total_flos": 2.922997874688e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null