Training in progress, step 200, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ad3613ef0ee29ca86146fd428cc0c1e08f6ddbc4972d2688ba40754f03cde58
+oid sha256:d69fb8c85d4f80ab6cc566a89ba99fd84ee51a696214294d5a3e19aeddfbe2d0
 size 3086634632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5c778279cf29494c876bb2e645da0a4341624e2f6a834a563dd661fcdfb1650
+oid sha256:1714eb9360923ab58d3ce7068cdb7aba99aab1210d50860621d5270d746c872b
 size 3136004290

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da0a5b26cef0a5106af3505cd537cb0ccd25d37dca9d04aeb79f08ffc4d4dd01
+oid sha256:f7b9a5d7f3f2c750cfe8b87de3aba151e04a9fad97837d71cb9d0140fc19145e
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b400d8747cfb55081da1a0068eee816c4d961918098df38f1b9b55162e6473d
+oid sha256:e1a78c2f428c2acad63e60b9927518355b75f220c1c223176c9d8a9cd76284e1
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6cd997f499454e13ac4dabde7c9b3fae456372bd14cee40bac36217d9c8b4b1
+oid sha256:9e85371deea3100d2ab445c982136740c600243d9badeb6e5c72c07324d88a6c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.054054054054054,
+  "epoch": 5.405405405405405,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 41.055,
       "eval_steps_per_second": 2.079,
       "step": 150
+    },
+    {
+      "epoch": 4.324324324324325,
+      "grad_norm": 1.5859375,
+      "learning_rate": 0.00019505909417784754,
+      "loss": 0.2196,
+      "step": 160
+    },
+    {
+      "epoch": 4.594594594594595,
+      "grad_norm": 0.9921875,
+      "learning_rate": 0.00019408298407861042,
+      "loss": 0.2407,
+      "step": 170
+    },
+    {
+      "epoch": 4.864864864864865,
+      "grad_norm": 1.03125,
+      "learning_rate": 0.00019302184919509755,
+      "loss": 0.2556,
+      "step": 180
+    },
+    {
+      "epoch": 5.135135135135135,
+      "grad_norm": 0.734375,
+      "learning_rate": 0.0001918766484973654,
+      "loss": 0.1991,
+      "step": 190
+    },
+    {
+      "epoch": 5.405405405405405,
+      "grad_norm": 0.828125,
+      "learning_rate": 0.0001906484169275263,
+      "loss": 0.1492,
+      "step": 200
+    },
+    {
+      "epoch": 5.405405405405405,
+      "eval_loss": 3.3331992626190186,
+      "eval_runtime": 34.9671,
+      "eval_samples_per_second": 42.926,
+      "eval_steps_per_second": 2.173,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -163,7 +206,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.830439793491968e+16,
+  "total_flos": 6.440586391322624e+16,
   "train_batch_size": 10,
   "trial_name": null,
   "trial_params": null