Training in progress, step 100, checkpoint

last-checkpoint/model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72fe86bc02adec23b28b68c15b10a96fd293a20ee6a1cdaafd0cf18e1685dc20
+oid sha256:861ef298194ce5f5a95b7fb9f3de924006083ce8f6c72fe8d11804878d22cf8d
 size 4874664552

last-checkpoint/model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0db6c3053a7deda030e77cbf9dc2889c468ba509b50f75ffb580a36cf57e0ef
+oid sha256:37c1108f60a343761b5ac77501f9ccf49e589e8a6d041d69da488eae8b26115a
 size 4932751008

last-checkpoint/model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d92a224e994fa1a22383ebe54bf00bb1077af44379b3bf42e7679b3dbab9987
+oid sha256:273aefb95ae0322c1ea6456d07840a68e51e7b149e3a956ddfd8f8329c4d22f2
 size 4330865200

last-checkpoint/model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdd5806b5d6ec7a64af996081c0f79be909a2e91f7faf708ef85bc77a39e2f04
+oid sha256:b0ef8a492aafc49d33deb349f2977b2c19503213b78477921a2921a786f30786
 size 1086998656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:264d9f5983d4e9539188419005a2b5a0ae23bbe058e7cb34ad670a166a35860a
+oid sha256:c60b475db0734986c42539b6a749e4d2824c9876d9e2050469711b4b0de5a01f
 size 15465450874

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2667eee8d875561f6539074432e0dd0e4895799b436b03ff4f88447a79b23c54
+oid sha256:f105b50093489fd740a8f6602ddfe873d388d5a0db4242d627bbb8ba93713d73
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f453d97040b5753e846b52c3f3f2ec936ae564e3d843c2334ebea047a9d227d
+oid sha256:9ac67ce68566e593180659981e408823cfcf7642579fefd1cbac723e565bb9c8
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c620e9c1e58182d1e495bef166b392358f6580ca0b286508365d4c14b06ac944
+oid sha256:43a0c31b135429597fb4601695aee5de28b0f5fb6a2c4e45d278a9e4001d0c26
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2617801047120419,
+  "epoch": 0.5235602094240838,
   "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": 24.869,
       "eval_steps_per_second": 6.23,
       "step": 50
+    },
+    {
+      "epoch": 0.31413612565445026,
+      "grad_norm": 3.71875,
+      "learning_rate": 0.00019998870284726968,
+      "loss": 2.4031,
+      "step": 60
+    },
+    {
+      "epoch": 0.36649214659685864,
+      "grad_norm": 3.359375,
+      "learning_rate": 0.00019989834093992945,
+      "loss": 2.5623,
+      "step": 70
+    },
+    {
+      "epoch": 0.418848167539267,
+      "grad_norm": 3.578125,
+      "learning_rate": 0.00019971769878721743,
+      "loss": 2.734,
+      "step": 80
+    },
+    {
+      "epoch": 0.4712041884816754,
+      "grad_norm": 3.21875,
+      "learning_rate": 0.00019944693963927092,
+      "loss": 2.7436,
+      "step": 90
+    },
+    {
+      "epoch": 0.5235602094240838,
+      "grad_norm": 5.75,
+      "learning_rate": 0.00019908630818686338,
+      "loss": 2.8422,
+      "step": 100
+    },
+    {
+      "epoch": 0.5235602094240838,
+      "eval_loss": 2.754179000854492,
+      "eval_runtime": 57.9266,
+      "eval_samples_per_second": 25.912,
+      "eval_steps_per_second": 6.491,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.737307157692416e+16,
+  "total_flos": 3.474614315384832e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null