Training in progress, step 400, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4cbb235c853766b6bfc3f92c5e43581833b06c318ff20cebbd9926e3ee0d673
+oid sha256:03438d87162fa3ae59956221d36f82a9321e50965d77bf13e46151829d5f6e80
 size 250490408

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e83c83741841127291068ca3f8911471f56d6b38a3a1f40a3c482d2c41d2eeca
+oid sha256:482c76b7e2b2dd94f963053f2b889f177b57ab782f96200808e7548078b9c06c
 size 255266042

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f80645c9c28658b6a91789122fec4c641bc39c0d4f1a7e56cb96853b18e402c
+oid sha256:57d0f1b7067c6220f6a5ca48baeecd587b394151cc545f90b6339e9e610bf246
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1d9325eceea92ca65820843d153b2cb31175794a5ccd0a723b229ca76e45f58
+oid sha256:d72484dfd8551a0f67ea47f28366dfee127e1515d7d6d10f8ca73a95bec2695e
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:972684576ff55802aec9ad573b837fe663d45ec783d38050b5b6dc1fc7271117
+oid sha256:0e4c78e85c4ba926d25150d4aaddeaf5728dcb066f4afc01202e3e56f29a5487
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 29.166666666666668,
+  "epoch": 33.333333333333336,
   "eval_steps": 50,
-  "global_step": 350,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -316,6 +316,49 @@
       "eval_samples_per_second": 145.068,
       "eval_steps_per_second": 2.32,
       "step": 350
+    },
+    {
+      "epoch": 30.0,
+      "grad_norm": 3.6875,
+      "learning_rate": 7.54514512859201e-05,
+      "loss": 2.6366,
+      "step": 360
+    },
+    {
+      "epoch": 30.833333333333332,
+      "grad_norm": 2.890625,
+      "learning_rate": 7.014851889983057e-05,
+      "loss": 2.6056,
+      "step": 370
+    },
+    {
+      "epoch": 31.666666666666668,
+      "grad_norm": 4.03125,
+      "learning_rate": 6.493624448072457e-05,
+      "loss": 2.5957,
+      "step": 380
+    },
+    {
+      "epoch": 32.5,
+      "grad_norm": 2.9375,
+      "learning_rate": 5.983045753470308e-05,
+      "loss": 2.5768,
+      "step": 390
+    },
+    {
+      "epoch": 33.333333333333336,
+      "grad_norm": 2.75,
+      "learning_rate": 5.484666416891109e-05,
+      "loss": 2.5792,
+      "step": 400
+    },
+    {
+      "epoch": 33.333333333333336,
+      "eval_loss": 3.1012673377990723,
+      "eval_runtime": 10.582,
+      "eval_samples_per_second": 141.844,
+      "eval_steps_per_second": 2.268,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -335,7 +378,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.267910316543181e+16,
+  "total_flos": 2.592225988129587e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null