Training in progress, step 40, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9b841b09c9dd8f6d4d92bae6a6575aadd48707d9b68b71831107d9f2bc76adb
+oid sha256:ae4abc05650849fb84375c4b3c802c9c9c31dbfb9c6d98acc14dce8fe584f12d
 size 2066752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fd23b2c7ff318c50bf906b4c5c4326c4f1fbed5724d8cbe6c56c8b59db03399
+oid sha256:5c62f06979cf820d1bc4612fea30f44881af3b0376093dca294382ee927a5438
 size 2162798

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ac85e2287c8599899f85951b17c5e4c4f197b5b4d1cc47f24edbb3e1bc0f460
+oid sha256:62f5415ab0d082726880d0dd73d69a20743d20a0a7c951a4836c628ef156f744
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c80ddb4d12adee2e9c1a55ece2b5416bdcce910d1d208bbc2d42ed23c071a2b
+oid sha256:1d64f701370aa11c801b0e964ae533eec7ae3c3c8e7535246f28875affe1de61
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3d7496cd5cad5fcd343f51f06f864ca525a833da3ba71e9c4d90915510423ac
+oid sha256:572996e9dc190ff3f3a6efdf58de929f593fa2dd2f97d74fed7646828651b17f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.5384615384615383,
+  "epoch": 3.076923076923077,
   "eval_steps": 40,
-  "global_step": 20,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -29,6 +29,28 @@
       "learning_rate": 0.00013333333333333334,
       "loss": 10.3754,
       "step": 20
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "grad_norm": 0.11279296875,
+      "learning_rate": 0.0002,
+      "loss": 10.3683,
+      "step": 30
+    },
+    {
+      "epoch": 3.076923076923077,
+      "grad_norm": 0.201171875,
+      "learning_rate": 0.00019984815164333163,
+      "loss": 10.3522,
+      "step": 40
+    },
+    {
+      "epoch": 3.076923076923077,
+      "eval_loss": 10.336621284484863,
+      "eval_runtime": 5.2692,
+      "eval_samples_per_second": 284.862,
+      "eval_steps_per_second": 4.555,
+      "step": 40
     }
   ],
   "logging_steps": 10,
@@ -48,7 +70,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8183170990080.0,
+  "total_flos": 16366341980160.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null