Training in progress, epoch 6, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8eca686f15f7d1e58e51f23b7954f46a4dad547a873578ae047493495e4b2367
+oid sha256:a9eb88a3e6d8f1712c426cf800d15df935a5e8b192520c93348d9a0147c06422
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:427e778d880924859223535a5405d79ec93decf7306db7898f3d2173df56cdca
+oid sha256:c0846f77e646761a15830dc85270fddffc481db0486cbb2371ef5bd57887333a
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0b85321ad738c74674d6af0fbf1d75c6dd6871a51c1df8a26d64be900bad3e4
+oid sha256:734f0a69b0cf6eb74829d78e6b046545419f2c52e87564748dc154c64cb11f14
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cad5f03d51098deec16f832dd35e17c987b9fec698c0d54d55ec05fc16c3cfe
+oid sha256:7f989cd76f71f8924a230ef13fb6c1924ade9bc322bba8404cad4cb6b7c6180b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.28598517179489136,
   "best_model_checkpoint": "./opt_trained/checkpoint-644",
-  "epoch": 5.0,
+  "epoch": 6.0,
   "eval_steps": 500,
-  "global_step": 1610,
+  "global_step": 1932,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -68,6 +68,14 @@
       "eval_samples_per_second": 24.764,
       "eval_steps_per_second": 6.191,
       "step": 1610
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.2881246507167816,
+      "eval_runtime": 115.3108,
+      "eval_samples_per_second": 24.768,
+      "eval_steps_per_second": 6.192,
+      "step": 1932
     }
   ],
   "logging_steps": 500,
@@ -87,7 +95,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.07476332224e+16,
+  "total_flos": 6.089715986688e+16,
   "train_batch_size": 10,
   "trial_name": null,
   "trial_params": null