Training in progress, step 250, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d69fb8c85d4f80ab6cc566a89ba99fd84ee51a696214294d5a3e19aeddfbe2d0
+oid sha256:57931ccc5ede5e9b408087ee39e0c8acfea478feb0db465454ea28f70f45fce8
 size 3086634632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1714eb9360923ab58d3ce7068cdb7aba99aab1210d50860621d5270d746c872b
+oid sha256:a670ff016a28acc74aa8c9382b99fae9c30939c44c51045fb6b5702d079ab4d8
 size 3136004290

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7b9a5d7f3f2c750cfe8b87de3aba151e04a9fad97837d71cb9d0140fc19145e
+oid sha256:d9d2eb4230608a2e50c5e2e997035fa89b37c3a1f78cd2d086d678da431507f0
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1a78c2f428c2acad63e60b9927518355b75f220c1c223176c9d8a9cd76284e1
+oid sha256:bc50388692076d892e9a6a3cc11b337ccbfc6d0655c35c5d50cb2003fe50a00f
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e85371deea3100d2ab445c982136740c600243d9badeb6e5c72c07324d88a6c
+oid sha256:15ba0115447c74c421f2515daef64bb4b3b3b78267a7971a106df2ae18c0ebef
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.405405405405405,
+  "epoch": 6.756756756756757,
   "eval_steps": 50,
-  "global_step": 200,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 42.926,
       "eval_steps_per_second": 2.173,
       "step": 200
+    },
+    {
+      "epoch": 5.675675675675675,
+      "grad_norm": 0.796875,
+      "learning_rate": 0.00018933826446444933,
+      "loss": 0.1548,
+      "step": 210
+    },
+    {
+      "epoch": 5.945945945945946,
+      "grad_norm": 1.1953125,
+      "learning_rate": 0.0001879473751206489,
+      "loss": 0.1538,
+      "step": 220
+    },
+    {
+      "epoch": 6.216216216216216,
+      "grad_norm": 0.546875,
+      "learning_rate": 0.0001864770058722676,
+      "loss": 0.0797,
+      "step": 230
+    },
+    {
+      "epoch": 6.486486486486487,
+      "grad_norm": 0.53515625,
+      "learning_rate": 0.00018492848552312014,
+      "loss": 0.0722,
+      "step": 240
+    },
+    {
+      "epoch": 6.756756756756757,
+      "grad_norm": 0.52734375,
+      "learning_rate": 0.00018330321350382544,
+      "loss": 0.0669,
+      "step": 250
+    },
+    {
+      "epoch": 6.756756756756757,
+      "eval_loss": 3.573293685913086,
+      "eval_runtime": 35.0908,
+      "eval_samples_per_second": 42.775,
+      "eval_steps_per_second": 2.166,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -206,7 +249,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.440586391322624e+16,
+  "total_flos": 8.05073298915328e+16,
   "train_batch_size": 10,
   "trial_name": null,
   "trial_params": null