Training in progress, step 7000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6312a7d18158015b6ca3368ce985616c02baba57e749583a73698e9311365a8
+oid sha256:6b6beb99d53dc85acda2f8ace3d229350875cf63a734ef325761a0e457e7f612
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:811f77f1e7a4d53f0449c64f994693035f7345177e8f1d35540ff8163935e513
+oid sha256:f2701e97535a87882ab713841abd901bf0568af17cf0a339a8c12431670adb4b
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ed5fba27a3a8a24d10b87fd853e1ccad54f52ff4b84d894d5cce98569dfa342
+oid sha256:9f110c3c4fe22448ff8783649fbef7b54b070a7c45b4469624f986b9a7cd74b3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7a7b1b30309b1c3b11ce15f113db2c6e3df169af496faf041634b692afa8937
+oid sha256:6ccfed333de7ee72e49042ff43701fa36052369ab2407e1f957a0a822d1a798f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.08321517705917358,
   "best_model_checkpoint": "./fine-tuned/checkpoint-6000",
-  "epoch": 1.04,
+  "epoch": 1.12,
   "eval_steps": 500,
-  "global_step": 6500,
+  "global_step": 7000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1021,6 +1021,84 @@
       "eval_samples_per_second": 17.125,
       "eval_steps_per_second": 2.141,
       "step": 6500
+    },
+    {
+      "epoch": 1.048,
+      "grad_norm": 6437.4033203125,
+      "learning_rate": 1.952e-05,
+      "loss": 0.0567,
+      "step": 6550
+    },
+    {
+      "epoch": 1.056,
+      "grad_norm": 5099.38330078125,
+      "learning_rate": 1.944e-05,
+      "loss": 0.0553,
+      "step": 6600
+    },
+    {
+      "epoch": 1.064,
+      "grad_norm": 5254.07275390625,
+      "learning_rate": 1.936e-05,
+      "loss": 0.0564,
+      "step": 6650
+    },
+    {
+      "epoch": 1.072,
+      "grad_norm": 7453.3330078125,
+      "learning_rate": 1.9280000000000002e-05,
+      "loss": 0.0573,
+      "step": 6700
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 3853.006103515625,
+      "learning_rate": 1.9200000000000003e-05,
+      "loss": 0.0607,
+      "step": 6750
+    },
+    {
+      "epoch": 1.088,
+      "grad_norm": 8804.1083984375,
+      "learning_rate": 1.912e-05,
+      "loss": 0.0578,
+      "step": 6800
+    },
+    {
+      "epoch": 1.096,
+      "grad_norm": 5899.22021484375,
+      "learning_rate": 1.904e-05,
+      "loss": 0.0555,
+      "step": 6850
+    },
+    {
+      "epoch": 1.104,
+      "grad_norm": 8429.76171875,
+      "learning_rate": 1.896e-05,
+      "loss": 0.0539,
+      "step": 6900
+    },
+    {
+      "epoch": 1.112,
+      "grad_norm": 9160.4794921875,
+      "learning_rate": 1.888e-05,
+      "loss": 0.0572,
+      "step": 6950
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 4707.27099609375,
+      "learning_rate": 1.8800000000000003e-05,
+      "loss": 0.0563,
+      "step": 7000
+    },
+    {
+      "epoch": 1.12,
+      "eval_loss": 0.08350159972906113,
+      "eval_runtime": 116.6938,
+      "eval_samples_per_second": 17.139,
+      "eval_steps_per_second": 2.142,
+      "step": 7000
     }
   ],
   "logging_steps": 50,
@@ -1040,7 +1118,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.166581030912e+16,
+  "total_flos": 3.410164187136e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null