Training in progress, step 6500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:595cdcb5015115c6cbe2e6edbc30ee6705f67aa46b94c988f719a34cfbffd2cf
+oid sha256:a6312a7d18158015b6ca3368ce985616c02baba57e749583a73698e9311365a8
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:413d3093ca25037d97577232c37b28c1f8751cf177fef08c1cb404465db4cfd4
+oid sha256:811f77f1e7a4d53f0449c64f994693035f7345177e8f1d35540ff8163935e513
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6703b98a291d6e4043156fd5230a9d97acbef451284cebbec159795253cbebaf
+oid sha256:5ed5fba27a3a8a24d10b87fd853e1ccad54f52ff4b84d894d5cce98569dfa342
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f222e945c4954eb35a2a25c9f653bde2dc7b8763271375e010f0439b14074e8d
+oid sha256:a7a7b1b30309b1c3b11ce15f113db2c6e3df169af496faf041634b692afa8937
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.08321517705917358,
   "best_model_checkpoint": "./fine-tuned/checkpoint-6000",
-  "epoch": 0.96,
+  "epoch": 1.04,
   "eval_steps": 500,
-  "global_step": 6000,
+  "global_step": 6500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -943,6 +943,84 @@
       "eval_samples_per_second": 17.142,
       "eval_steps_per_second": 2.143,
       "step": 6000
+    },
+    {
+      "epoch": 0.968,
+      "grad_norm": 5835.19189453125,
+      "learning_rate": 2.0320000000000002e-05,
+      "loss": 0.0643,
+      "step": 6050
+    },
+    {
+      "epoch": 0.976,
+      "grad_norm": 5896.76318359375,
+      "learning_rate": 2.024e-05,
+      "loss": 0.0625,
+      "step": 6100
+    },
+    {
+      "epoch": 0.984,
+      "grad_norm": 6958.45751953125,
+      "learning_rate": 2.016e-05,
+      "loss": 0.0657,
+      "step": 6150
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 4680.04736328125,
+      "learning_rate": 2.008e-05,
+      "loss": 0.0632,
+      "step": 6200
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 8230.8056640625,
+      "learning_rate": 1.9999999999999998e-05,
+      "loss": 0.0603,
+      "step": 6250
+    },
+    {
+      "epoch": 1.008,
+      "grad_norm": 5693.77001953125,
+      "learning_rate": 1.9920000000000002e-05,
+      "loss": 0.0574,
+      "step": 6300
+    },
+    {
+      "epoch": 1.016,
+      "grad_norm": 14030.3583984375,
+      "learning_rate": 1.984e-05,
+      "loss": 0.0563,
+      "step": 6350
+    },
+    {
+      "epoch": 1.024,
+      "grad_norm": 11693.09375,
+      "learning_rate": 1.976e-05,
+      "loss": 0.0558,
+      "step": 6400
+    },
+    {
+      "epoch": 1.032,
+      "grad_norm": 5772.1845703125,
+      "learning_rate": 1.968e-05,
+      "loss": 0.0544,
+      "step": 6450
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 8641.919921875,
+      "learning_rate": 1.96e-05,
+      "loss": 0.0606,
+      "step": 6500
+    },
+    {
+      "epoch": 1.04,
+      "eval_loss": 0.08356834203004837,
+      "eval_runtime": 116.7914,
+      "eval_samples_per_second": 17.125,
+      "eval_steps_per_second": 2.141,
+      "step": 6500
     }
   ],
   "logging_steps": 50,
@@ -962,7 +1040,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.922997874688e+16,
+  "total_flos": 3.166581030912e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null