Training in progress, step 1000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd5dde95ad6c157a2fe95cc958dbb18c26699082da64c338dab9848d4c67c19a
+oid sha256:afcd81be9b532c2a51334c9b2205e5e3b2dce963888b7a4276a6b07b3407d7e6
 size 540827680

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ea50f6e51285e2a51883bc21cde22e02fb19d673bd8e39e2afff7b2db706d12
+oid sha256:04e54ceee3605ff92754bffa78afc73aed9dbc57e9fd6a5462119c931d361160
 size 1081770746

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06e55bfc8723f269a626afca0be6f7def5753f3bb265436b94c5580b703cfcc7
+oid sha256:7bc6631138e7fa84a7a9d65acc91ce044a760be23ac04a06a280bdd1e0066a08
 size 13990

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8967d5c23dc2de82573da94680305eacf32d7b908df4950b6f5a1314e5be47e
+oid sha256:5e29425e5a8e130a3001b6471b34f1175bdf6c6c4e0d2fe18e68d527d7f30011
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7994011976047904,
-  "best_model_checkpoint": "./results/checkpoint-500",
-  "epoch": 1.3333333333333333,
+  "best_metric": 0.8383233532934131,
+  "best_model_checkpoint": "./results/checkpoint-1000",
+  "epoch": 2.6666666666666665,
   "eval_steps": 250,
-  "global_step": 500,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,143 @@
       "eval_samples_per_second": 2.658,
       "eval_steps_per_second": 0.334,
       "step": 500
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 13.776785850524902,
+      "learning_rate": 1.0933333333333334e-05,
+      "loss": 0.4696,
+      "step": 510
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 24.468957901000977,
+      "learning_rate": 1.04e-05,
+      "loss": 0.617,
+      "step": 540
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 18.628131866455078,
+      "learning_rate": 9.866666666666668e-06,
+      "loss": 0.6078,
+      "step": 570
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 100.15174865722656,
+      "learning_rate": 9.333333333333334e-06,
+      "loss": 0.5287,
+      "step": 600
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 16.748079299926758,
+      "learning_rate": 8.8e-06,
+      "loss": 0.7787,
+      "step": 630
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 19.134979248046875,
+      "learning_rate": 8.266666666666667e-06,
+      "loss": 0.4815,
+      "step": 660
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 6.146342754364014,
+      "learning_rate": 7.733333333333334e-06,
+      "loss": 0.5385,
+      "step": 690
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 5.284756660461426,
+      "learning_rate": 7.2000000000000005e-06,
+      "loss": 0.6076,
+      "step": 720
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 13.146005630493164,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.5023,
+      "step": 750
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8323353293413174,
+      "eval_loss": 0.6021029353141785,
+      "eval_runtime": 118.5789,
+      "eval_samples_per_second": 2.817,
+      "eval_steps_per_second": 0.354,
+      "step": 750
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 15.934453010559082,
+      "learning_rate": 6.133333333333334e-06,
+      "loss": 0.4482,
+      "step": 780
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 2.5525577068328857,
+      "learning_rate": 5.600000000000001e-06,
+      "loss": 0.4262,
+      "step": 810
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 20.71769905090332,
+      "learning_rate": 5.0666666666666676e-06,
+      "loss": 0.3308,
+      "step": 840
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 5.773500919342041,
+      "learning_rate": 4.533333333333334e-06,
+      "loss": 0.3913,
+      "step": 870
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 23.659786224365234,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.4899,
+      "step": 900
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 9.76993179321289,
+      "learning_rate": 3.4666666666666672e-06,
+      "loss": 0.3889,
+      "step": 930
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 3.7444443702697754,
+      "learning_rate": 2.9333333333333338e-06,
+      "loss": 0.4644,
+      "step": 960
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 15.488058090209961,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.3985,
+      "step": 990
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "eval_accuracy": 0.8383233532934131,
+      "eval_loss": 0.5776464939117432,
+      "eval_runtime": 128.183,
+      "eval_samples_per_second": 2.606,
+      "eval_steps_per_second": 0.328,
+      "step": 1000
     }
   ],
   "logging_steps": 30,
@@ -172,7 +309,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 262998389326848.0,
+  "total_flos": 525996778653696.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null