Training in progress, epoch 8, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e777e0edeae43d15f56f74eb543664fe669a5ec505a9a88b757748b46e9665ee
+oid sha256:d9521d45ffde9e744a59ae0a218b76ee9dbb22362782eba61d3452f92bfb42ac
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c40d6c6d56b7bb73b23fcae21fdab9927b34c54ee0f8338dd9ba20cd4851366c
+oid sha256:bb58efc731f5e9f91bb0a3b0b5d2ddd6631a24ee4477a9314d268b511c0900f3
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ed244f721b9495a7585428e681f68fc58fe0408c52158c97e3cc0c7c1263a36
+oid sha256:5e89c896d5de675a65aad5262ac3f12ebbd8dd5c6d70c67b825651cc5237f1b2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:365454e802f0a892dbea708dd49306c6b18204078d3c51c7cf9ecfc02f6f045f
+oid sha256:bb7d986c9dd9650a7210dfcb89384b6f70fd4c8bf29e97d4befff946cb6fd316
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.29741692543029785,
-  "best_model_checkpoint": "./opt_trained/checkpoint-1610",
-  "epoch": 7.0,
+  "best_metric": 0.29721641540527344,
+  "best_model_checkpoint": "./opt_trained/checkpoint-2576",
+  "epoch": 8.0,
   "eval_steps": 500,
-  "global_step": 2254,
+  "global_step": 2576,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -91,6 +91,21 @@
       "eval_samples_per_second": 19.559,
       "eval_steps_per_second": 4.89,
       "step": 2254
+    },
+    {
+      "epoch": 7.765758754863813,
+      "grad_norm": 2.2594358921051025,
+      "learning_rate": 2.6818939512889293e-05,
+      "loss": 0.2897,
+      "step": 2500
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.29721641540527344,
+      "eval_runtime": 146.0416,
+      "eval_samples_per_second": 19.556,
+      "eval_steps_per_second": 4.889,
+      "step": 2576
     }
   ],
   "logging_steps": 500,
@@ -110,7 +125,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.399458267136e+16,
+  "total_flos": 1.0742238019584e+17,
   "train_batch_size": 10,
   "trial_name": null,
   "trial_params": null