Training in progress, step 10000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e166df977f21f4e74668f730deac309df6a571f19acaa0dfa89c2e3c2819431
+oid sha256:5eb8bf06dd538fcb262c2fed2f9e68d7952360b525571db7ca0f1430e447d9ed
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e99baec34b5da3301e09eb5c4f9d3ef873b304cf96feddd1cfe61690f168589
+oid sha256:942c2875abedaddb5c9436b198254369aa4f7b28a3b4b68fd6fcf41053e028fd
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91f8e7f84c942f83f5d877ebb335efd09f2d70c83c135e4e031bf84b0af23af9
+oid sha256:7a7ea66d1531ee601a7eaa0403a8186669a6c59db91f4cad349d74bc0115c72f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e8e6e071a0a58044a0e6d93d2bb93dd252e4dfa6d5810853dc9dadf39da6ab9
+oid sha256:7631547026bec9cd7a6ea58b5f8fb2fb117b688cae951965f0f9ff628a1476de
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.08252418041229248,
-  "best_model_checkpoint": "./fine-tuned/checkpoint-9500",
-  "epoch": 1.52,
+  "best_metric": 0.08249519765377045,
+  "best_model_checkpoint": "./fine-tuned/checkpoint-10000",
+  "epoch": 1.6,
   "eval_steps": 500,
-  "global_step": 9500,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1489,6 +1489,84 @@
       "eval_samples_per_second": 17.137,
       "eval_steps_per_second": 2.142,
       "step": 9500
+    },
+    {
+      "epoch": 1.528,
+      "grad_norm": 6762.00244140625,
+      "learning_rate": 1.472e-05,
+      "loss": 0.0529,
+      "step": 9550
+    },
+    {
+      "epoch": 1.536,
+      "grad_norm": 7704.66748046875,
+      "learning_rate": 1.464e-05,
+      "loss": 0.0576,
+      "step": 9600
+    },
+    {
+      "epoch": 1.544,
+      "grad_norm": 5400.18798828125,
+      "learning_rate": 1.4560000000000001e-05,
+      "loss": 0.0556,
+      "step": 9650
+    },
+    {
+      "epoch": 1.552,
+      "grad_norm": 6167.47216796875,
+      "learning_rate": 1.448e-05,
+      "loss": 0.0547,
+      "step": 9700
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 5073.39892578125,
+      "learning_rate": 1.44e-05,
+      "loss": 0.0544,
+      "step": 9750
+    },
+    {
+      "epoch": 1.568,
+      "grad_norm": 6849.08447265625,
+      "learning_rate": 1.432e-05,
+      "loss": 0.0571,
+      "step": 9800
+    },
+    {
+      "epoch": 1.576,
+      "grad_norm": 6866.765625,
+      "learning_rate": 1.4240000000000001e-05,
+      "loss": 0.0518,
+      "step": 9850
+    },
+    {
+      "epoch": 1.584,
+      "grad_norm": 8185.33740234375,
+      "learning_rate": 1.416e-05,
+      "loss": 0.0605,
+      "step": 9900
+    },
+    {
+      "epoch": 1.592,
+      "grad_norm": 7759.45361328125,
+      "learning_rate": 1.408e-05,
+      "loss": 0.0581,
+      "step": 9950
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 5736.8740234375,
+      "learning_rate": 1.4e-05,
+      "loss": 0.0582,
+      "step": 10000
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 0.08249519765377045,
+      "eval_runtime": 116.9496,
+      "eval_samples_per_second": 17.101,
+      "eval_steps_per_second": 2.138,
+      "step": 10000
     }
   ],
   "logging_steps": 50,
@@ -1508,7 +1586,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.628079968256e+16,
+  "total_flos": 4.87166312448e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null