Training in progress, step 100, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c18b4cf96983818fb58b4a5e336f7b4a778ac8603896037ce0c1a673994e7518
+oid sha256:11a9b69a02962a84d97f38904eabe5b4f53cc044fc070efd4a92ce22c97e4e05
 size 250490408

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7fb381715a6f4a8adab9f7d14d2d354ecb9694c12411525b7da9969b9055c04
+oid sha256:cd5b3908315305669c6ecf2973c1e26d14718d1532bcd29022c36b98c149b484
 size 255265850

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5893d9851ea92670a3d4726f43f20d99c50539fb42caed0b0dc2086e89cfc271
+oid sha256:5e4027fefb69e105f5311c9cb16f281c69cccb2a472492c81e3a929896e7e87d
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:683aee245ed54365847ef67e55fa73019e878211c9d91ace134780fe9514381e
+oid sha256:4791734ef084625a7f903446f63b41709ec4aa45432e4cf043c49101a53ddaee
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b5bd1b09d58ee3e65553e6f9772dc7c5ca98238b1cade33cccd500df2328864
+oid sha256:d429d3d3635edcf38935f000b0d1f4e5db465042c289fb4623c33dce588231ab
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.166666666666667,
+  "epoch": 8.333333333333334,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 138.368,
       "eval_steps_per_second": 2.212,
       "step": 50
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 7.0625,
+      "learning_rate": 0.00019863613034027224,
+      "loss": 4.772,
+      "step": 60
+    },
+    {
+      "epoch": 5.833333333333333,
+      "grad_norm": 4.53125,
+      "learning_rate": 0.00019757963826274357,
+      "loss": 4.671,
+      "step": 70
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 5.46875,
+      "learning_rate": 0.00019622680003092503,
+      "loss": 4.4709,
+      "step": 80
+    },
+    {
+      "epoch": 7.5,
+      "grad_norm": 3.796875,
+      "learning_rate": 0.00019458172417006347,
+      "loss": 4.3646,
+      "step": 90
+    },
+    {
+      "epoch": 8.333333333333334,
+      "grad_norm": 3.875,
+      "learning_rate": 0.00019264940672148018,
+      "loss": 4.2165,
+      "step": 100
+    },
+    {
+      "epoch": 8.333333333333334,
+      "eval_loss": 3.1671667098999023,
+      "eval_runtime": 10.6557,
+      "eval_samples_per_second": 140.864,
+      "eval_steps_per_second": 2.252,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3242111495307264.0,
+  "total_flos": 6486313364619264.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null