Training in progress, epoch 3, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2034bb97f4730139642eb3804cfcc23e3e7ae555351b5d9b5b1144ed6ab06648
+oid sha256:05d56ff701af02fe605448b713a4f4a3e1e8e81f1fd16e297a520155e4f93801
 size 1324830880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b5abddcf41715edb74a3561fb07fd74da8c594dec7a45ab2714cf75ed7b5996
+oid sha256:6cba132f52109527b9ee2728ac354f4960ec64c5865c2c73114020bd19897561
 size 2649896030

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b19017691ba1183e28fdb61b4af9141a4d5260985dada79dc93c86adebcea5df
+oid sha256:1de4498a0de62c098b1cb8172b9b1220b1b62c62b8e96d152d6e567f4efc9a50
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16aae2bd78e4d4da557759bb72d80c4f5d11afb7de0a65ba2d7641cf4fc763af
+oid sha256:05e2d1622657dcc0dcd51ce58722af936ea03498ab99a1d3c8cd80669cb28819
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.431854248046875,
   "best_model_checkpoint": "./opt_trained1/checkpoint-268",
-  "epoch": 2.0,
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 536,
+  "global_step": 804,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,14 @@
       "eval_samples_per_second": 13.789,
       "eval_steps_per_second": 1.724,
       "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 4.4594879150390625,
+      "eval_runtime": 207.2002,
+      "eval_samples_per_second": 13.784,
+      "eval_steps_per_second": 1.723,
+      "step": 804
     }
   ],
   "logging_steps": 500,
@@ -49,7 +57,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.619897028591616e+16,
+  "total_flos": 5.429845542887424e+16,
   "train_batch_size": 12,
   "trial_name": null,
   "trial_params": null