Training in progress, step 180, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b7cee3922fcc03ddd02b462320d72e817bf48e4d821bc9bc174cfffb0ecea99
+oid sha256:e00b3e4d14bfa2e93fb7b485f252d1a537d486247617da04e0d7a00869f3b466
 size 2066752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68f934757bee3b96c44f1fcd5f66f7c21d6d690ac6920e0836e32f7839398948
+oid sha256:467d667b0f7dbcb055a69972708269307511838923df8ff544a1486a01d1e192
 size 2162798

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:913640eb3030e6918a3ab32d574e4ce2a40a5f144929ffe8d31bd7f1b358f50e
+oid sha256:7aa924273901c1feaf439a41005e26ed218c16fdbbc3c727286f31e31d59848e
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acd82ba45bf646ef902426ab4e034c595d02ef045ce9b7e0cd2cf700f65691a7
+oid sha256:9b775d676964eba957907c0ea3d5c5f814cabf4fc06c6838b05e1a89d80849d1
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf268cb489a17b00a5da2e7f7b4a75dcc816743c1b54be7c48bf73c90d10ecf4
+oid sha256:9f9f0e9fcb3fec99611921d8f34980406ad06f308daea00535e4da9839a46d96
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 12.307692307692308,
+  "epoch": 13.846153846153847,
   "eval_steps": 40,
-  "global_step": 160,
+  "global_step": 180,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -159,6 +159,20 @@
       "eval_samples_per_second": 282.81,
       "eval_steps_per_second": 4.522,
       "step": 160
+    },
+    {
+      "epoch": 13.076923076923077,
+      "grad_norm": 0.3671875,
+      "learning_rate": 0.00017167825131684513,
+      "loss": 9.6416,
+      "step": 170
+    },
+    {
+      "epoch": 13.846153846153847,
+      "grad_norm": 0.375,
+      "learning_rate": 0.00016772815716257412,
+      "loss": 9.597,
+      "step": 180
     }
   ],
   "logging_steps": 10,
@@ -178,7 +192,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 65465367920640.0,
+  "total_flos": 73648538910720.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null