Training in progress, epoch 7, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ef2964c596680496bac1a5fde881df5501c7c42822b39cd64932847d5d20b51
+oid sha256:e777e0edeae43d15f56f74eb543664fe669a5ec505a9a88b757748b46e9665ee
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12f7764af7f92a2663cb676fefbb2e8350dab83243e3739b4d7d76ba820aa83c
+oid sha256:c40d6c6d56b7bb73b23fcae21fdab9927b34c54ee0f8338dd9ba20cd4851366c
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e9e9b1b8a737a0e6724d8363ae32af08a7ae44ac84fc74cf26efc38d72c2e99
+oid sha256:3ed244f721b9495a7585428e681f68fc58fe0408c52158c97e3cc0c7c1263a36
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dbd5ff4bdf3d44747ad00fa29200a8d92013019282f4c83378b09ca4fd6fe51
+oid sha256:365454e802f0a892dbea708dd49306c6b18204078d3c51c7cf9ecfc02f6f045f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.29741692543029785,
   "best_model_checkpoint": "./opt_trained/checkpoint-1610",
-  "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": 19.627,
       "eval_steps_per_second": 4.907,
       "step": 1932
+    },
+    {
+      "epoch": 6.211673151750973,
+      "grad_norm": 2.5450387001037598,
+      "learning_rate": 3.11703315146825e-05,
+      "loss": 0.292,
+      "step": 2000
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.29770833253860474,
+      "eval_runtime": 146.0174,
+      "eval_samples_per_second": 19.559,
+      "eval_steps_per_second": 4.89,
+      "step": 2254
     }
   ],
   "logging_steps": 500,
@@ -95,7 +110,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.056678514688e+16,
+  "total_flos": 9.399458267136e+16,
   "train_batch_size": 10,
   "trial_name": null,
   "trial_params": null