Training in progress, step 1000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27aaf51be344fdf558ecda990badb9c0fdb702501a800115667ae1d0d458d889
+oid sha256:b65f0032ace99ac31a5c4eaebab678922f9196855254a04fa04cd5b09838cd25
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00a78e6cd589620568cd11a8124efee25dc321c57212def3a84623d827f77b81
+oid sha256:9542f526fbcdae270a597291ca95babaa9f3b9e2d72ac373956f44fc941c5cd5
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba54176b539b14420803d3eda38f203f6842a1039f04005978b1bad7976f5771
+oid sha256:c88b9beda061d1039d8d779edfe7f5a8ca6add672a561cd18d21ff3443068c38
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97d0c42656677b3669a5e5760b1be71be06a3cd2fb44d0f56b707a5adc9d4f45
+oid sha256:635e57a0f4914cbbb1c670a34423e0edc1f884281d003185692f1319d135cdd1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.09235642850399017,
-  "best_model_checkpoint": "./fine-tuned/checkpoint-500",
-  "epoch": 0.08,
+  "best_metric": 0.08949962258338928,
+  "best_model_checkpoint": "./fine-tuned/checkpoint-1000",
+  "epoch": 0.16,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -81,10 +81,88 @@
     {
       "epoch": 0.08,
       "eval_loss": 0.09235642850399017,
-      "eval_runtime": 116.7651,
-      "eval_samples_per_second": 17.128,
-      "eval_steps_per_second": 2.141,
+      "eval_runtime": 109.274,
+      "eval_samples_per_second": 18.303,
+      "eval_steps_per_second": 2.288,
       "step": 500
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 6587.6513671875,
+      "learning_rate": 2.9120000000000002e-05,
+      "loss": 0.0815,
+      "step": 550
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 6632.0947265625,
+      "learning_rate": 2.904e-05,
+      "loss": 0.0794,
+      "step": 600
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 9301.228515625,
+      "learning_rate": 2.896e-05,
+      "loss": 0.076,
+      "step": 650
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 10575.0791015625,
+      "learning_rate": 2.888e-05,
+      "loss": 0.0791,
+      "step": 700
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 8609.86328125,
+      "learning_rate": 2.88e-05,
+      "loss": 0.0799,
+      "step": 750
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 11379.4423828125,
+      "learning_rate": 2.8720000000000003e-05,
+      "loss": 0.0759,
+      "step": 800
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 8489.6904296875,
+      "learning_rate": 2.864e-05,
+      "loss": 0.0753,
+      "step": 850
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 12353.6279296875,
+      "learning_rate": 2.856e-05,
+      "loss": 0.075,
+      "step": 900
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 11535.3994140625,
+      "learning_rate": 2.8480000000000002e-05,
+      "loss": 0.0757,
+      "step": 950
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 8291.939453125,
+      "learning_rate": 2.84e-05,
+      "loss": 0.0753,
+      "step": 1000
+    },
+    {
+      "epoch": 0.16,
+      "eval_loss": 0.08949962258338928,
+      "eval_runtime": 109.2536,
+      "eval_samples_per_second": 18.306,
+      "eval_steps_per_second": 2.288,
+      "step": 1000
     }
   ],
   "logging_steps": 50,
@@ -104,7 +182,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2435831562240000.0,
+  "total_flos": 4871663124480000.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null