Training in progress, step 200, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f2be77f4046d57162a2a1634e71c05173859bf5557783dfa12ea6e9468e051d
+oid sha256:39c3b834cf9097711f0f2aa3a630bfaed237e4d3c047f886943b7d264f08b96d
 size 723674912

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19b0ef4a865592b1c1398462392fee5da43bb5d95cb04ee8282d992c017e215b
+oid sha256:2174e639123eed1cb0a5141bbd6b84d6d9dc13c0802383f9c30c1c1f8eda9355
 size 735625370

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5179acd504f9caefc428bad8368a9feed783597605227f04c17ed5843af96dfc
+oid sha256:8eccf36684d22a967cc11b19ade6c5b107783ceb47a439463ddecc8296fd8bf9
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d57da5f6b8845015897fecc79abf7ca6507809cfcf86ed0e80e8a671f77e231
+oid sha256:32507bbe816cbd0427cff7ac83a89a718c120d506907cf5a125998e66e6121c4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2f8edafee3984ce0824458e1123790dbcab896cab979f7abfa8851dd911b81b
+oid sha256:d9b81926aa60404a196dbb989a6c6ee8f1074bab84733386986ddfa2847703b0
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:982ef26a1a303041dac26c15f97f86f53c622fcb36d57d2226e4c72f425873e3
+oid sha256:d5374c1c7c5169dac1e64e286b9ca7aa3607197c4f7671202eddd71042127d0a
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:723432e9081dffbc4dea9b11807f9120cba5ae794b58bf13637161ca198c867f
+oid sha256:ca9a25c72339c898b564e0c464a3f6fc75bbeec408008928b7ed05533156b98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 22.5,
+  "epoch": 25.0,
   "eval_steps": 20,
-  "global_step": 180,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -213,6 +213,28 @@
       "eval_samples_per_second": 300.65,
       "eval_steps_per_second": 3.405,
       "step": 180
+    },
+    {
+      "epoch": 23.75,
+      "grad_norm": 0.146484375,
+      "learning_rate": 1.3638696597277679e-06,
+      "loss": 2.0059,
+      "step": 190
+    },
+    {
+      "epoch": 25.0,
+      "grad_norm": 0.1318359375,
+      "learning_rate": 0.0,
+      "loss": 2.0109,
+      "step": 200
+    },
+    {
+      "epoch": 25.0,
+      "eval_loss": 2.0673062801361084,
+      "eval_runtime": 4.8758,
+      "eval_samples_per_second": 307.844,
+      "eval_steps_per_second": 3.487,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -227,12 +249,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.402489065039462e+16,
+  "total_flos": 7.113876738932736e+16,
   "train_batch_size": 23,
   "trial_name": null,
   "trial_params": null