Training in progress, epoch 3, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81ed38c2dece7acf1bf37c0cdb65ecc0014c3d4376e00086cef4fa399dc609fc
+oid sha256:8cb7fdd07abfa119cf7164e53299c607359a9af6799573cd9441c500a5e24222
 size 2609498088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e1cdeff63fa52ae131c44f61b169ab4ddcd7cb5ae622e4882f4bf017da7b19c
+oid sha256:c8434daa3277e8b219eb59a6668bc14f8e7e4908bd17a2304d8b94d800e65d92
 size 5208796146

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32b8788e687b5b213e4a1b56f7182c153e71fe454bb8e7faaeec16196cacd022
+oid sha256:e8bb9aa3709cd1c036484251854b8be7d825e637d956e7203821b032aa2540e3
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e8b7bfccb9c07860bceffabef3a52060cc451a19d3abd90d284c09f7120dba6
+oid sha256:541d8b16c337fd96e05a077a2be76d2de8216d931de0afb127b2cab79028732a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.0,
+  "epoch": 3.0,
   "eval_steps": 50,
-  "global_step": 258,
+  "global_step": 387,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -82,6 +82,36 @@
       "eval_samples_per_second": 37.501,
       "eval_steps_per_second": 18.75,
       "step": 250
+    },
+    {
+      "epoch": 2.32796486090776,
+      "grad_norm": 0.5856680274009705,
+      "learning_rate": 7.65625e-05,
+      "loss": 1.302,
+      "step": 300
+    },
+    {
+      "epoch": 2.32796486090776,
+      "eval_loss": 1.3940138816833496,
+      "eval_runtime": 11.5409,
+      "eval_samples_per_second": 37.432,
+      "eval_steps_per_second": 18.716,
+      "step": 300
+    },
+    {
+      "epoch": 2.7183992191312836,
+      "grad_norm": 0.5735114216804504,
+      "learning_rate": 7.265625000000001e-05,
+      "loss": 1.3063,
+      "step": 350
+    },
+    {
+      "epoch": 2.7183992191312836,
+      "eval_loss": 1.3489629030227661,
+      "eval_runtime": 11.5502,
+      "eval_samples_per_second": 37.402,
+      "eval_steps_per_second": 18.701,
+      "step": 350
     }
   ],
   "logging_steps": 50,
@@ -101,7 +131,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.13263584074793e+16,
+  "total_flos": 1.0698953774543667e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null