Training in progress, step 9, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87fe88de4833fabc6ccb9c3dfdbd970c638bdfca11344dd77472ca8d985c95a3
+oid sha256:0ccbd87296fe7edfb62b00c7c2773bb390eed1a2e39b5709993405542a238de7
 size 58562260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:192b4374c9fc5a11f6109cda2659cf69fbb9ede975a10eff99653276e17a86e4
+oid sha256:bbcb7350e6f7badaa842375dcfe363bace4f95510b2ff76b2e1bf21fbecd71e1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00821917808219178,
+  "epoch": 0.012328767123287671,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 13.201,
       "eval_steps_per_second": 6.601,
       "step": 6
+    },
+    {
+      "epoch": 0.009589041095890411,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.010958904109589041,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016,
+      "loss": 19.4086,
+      "step": 8
+    },
+    {
+      "epoch": 0.012328767123287671,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.012328767123287671,
+      "eval_loss": NaN,
+      "eval_runtime": 23.3177,
+      "eval_samples_per_second": 13.209,
+      "eval_steps_per_second": 6.604,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3208606226841600.0,
+  "total_flos": 4705955799367680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null