Training in progress, epoch 7, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9eb88a3e6d8f1712c426cf800d15df935a5e8b192520c93348d9a0147c06422
+oid sha256:a4523a9c93b74b8c5c6c35d9977a37738c2da28419bfceec3dc2abc9f3fea4fc
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0846f77e646761a15830dc85270fddffc481db0486cbb2371ef5bd57887333a
+oid sha256:053550d54418a8a41e8640524ab398a874541d31509cb91da0928e8cd3937d51
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:734f0a69b0cf6eb74829d78e6b046545419f2c52e87564748dc154c64cb11f14
+oid sha256:aa26de2555f562032c37435ab63a13624ac910b9318e07a207eeee632f850008
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f989cd76f71f8924a230ef13fb6c1924ade9bc322bba8404cad4cb6b7c6180b
+oid sha256:f7f6bb8605f469a84fbad16fb286e3274b0712f3f3c877543edc1e6dc05b8980
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.28598517179489136,
   "best_model_checkpoint": "./opt_trained/checkpoint-644",
-  "epoch": 6.0,
+  "epoch": 7.0,
   "eval_steps": 500,
-  "global_step": 1932,
+  "global_step": 2254,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -76,6 +76,21 @@
       "eval_samples_per_second": 24.768,
       "eval_steps_per_second": 6.192,
       "step": 1932
+    },
+    {
+      "epoch": 6.211673151750973,
+      "grad_norm": 3.0973498821258545,
+      "learning_rate": 3.1162212014830765e-05,
+      "loss": 0.2787,
+      "step": 2000
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.2881006598472595,
+      "eval_runtime": 115.2521,
+      "eval_samples_per_second": 24.78,
+      "eval_steps_per_second": 6.195,
+      "step": 2254
     }
   ],
   "logging_steps": 500,
@@ -95,7 +110,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.089715986688e+16,
+  "total_flos": 7.104668651136e+16,
   "train_batch_size": 10,
   "trial_name": null,
   "trial_params": null