Training in progress, step 100, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:766cd54d702e68387e8a47e9d3324fdfdbfc71c54ddeef13d62611ad5f472b94
+oid sha256:40c2ecd92e57b2e66ca22969473f53cb6e090828806462e132c671e6e2d3f419
 size 2066752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b5bb660eb4533fdec1208a7777e32810eec328387b3ef7df3ee27820b9acfd8
+oid sha256:62b8912999820c91e1c8c8c8687a2636c8a6f4f493c6ac56b50cf98a74706856
 size 2162798

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62f5415ab0d082726880d0dd73d69a20743d20a0a7c951a4836c628ef156f744
+oid sha256:bddb8fcdae8dea7e10388731f63246ec0494e51d6d509273113166b14d83f0e3
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d64f701370aa11c801b0e964ae533eec7ae3c3c8e7535246f28875affe1de61
+oid sha256:24238ca2ad5e52c7a2d983c253be8a0ab25f258c2785c7ba56c4bfa08fb89d84
 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": 3.8461538461538463,
+  "epoch": 7.6923076923076925,
   "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": 284.681,
       "eval_steps_per_second": 4.552,
       "step": 50
+    },
+    {
+      "epoch": 4.615384615384615,
+      "grad_norm": 0.32421875,
+      "learning_rate": 0.00019863613034027224,
+      "loss": 10.2518,
+      "step": 60
+    },
+    {
+      "epoch": 5.384615384615385,
+      "grad_norm": 0.326171875,
+      "learning_rate": 0.00019757963826274357,
+      "loss": 10.1828,
+      "step": 70
+    },
+    {
+      "epoch": 6.153846153846154,
+      "grad_norm": 0.330078125,
+      "learning_rate": 0.00019622680003092503,
+      "loss": 10.1177,
+      "step": 80
+    },
+    {
+      "epoch": 6.923076923076923,
+      "grad_norm": 0.33203125,
+      "learning_rate": 0.00019458172417006347,
+      "loss": 10.0565,
+      "step": 90
+    },
+    {
+      "epoch": 7.6923076923076925,
+      "grad_norm": 0.341796875,
+      "learning_rate": 0.00019264940672148018,
+      "loss": 9.998,
+      "step": 100
+    },
+    {
+      "epoch": 7.6923076923076925,
+      "eval_loss": 9.973793029785156,
+      "eval_runtime": 5.2822,
+      "eval_samples_per_second": 284.164,
+      "eval_steps_per_second": 4.544,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 20457927475200.0,
+  "total_flos": 40915854950400.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null