Training in progress, step 200, checkpoint

last-checkpoint/model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbcdf15b49c41eac5733b7951a6256902b8d1e91b700f5772dfc55598665a3d9
+oid sha256:32fdf89f0fd7dd6fbe9eeacac4a67aa119b62a3a4e0bb2532c080fcaaa3927fa
 size 4956450288

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a4c1b79856cf6a3f0ef4c01f5e8412c010f860d594ab1952bcba917ef64fe45
+oid sha256:7f17a270ec2582d3b80ca44646e38c1190ad03af747fc0196f9aa1f5b4ad2196
 size 1214366696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0bd0b7ce14e4324d40576d53e0125721f20ef228523334415572156c4e707e1
+oid sha256:243666f1190af6ded0e54e42649b5282ba9c715d9bcc56b00f78ffd8c0cfff34
 size 6269038402

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd0b45e6fd019f23318ffd2d46ef8cf6d2a160038f49f06fc17960b67863906f
+oid sha256:a4ffbd45539607b0e8b66094865a0f7f706b47ca1ed1a4ec5be6fc18e090daa0
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e71e2096e47d5825ef2ce323a1cf303b37363e73043bd284a3ba35f73c6da6e
+oid sha256:3a5f77331c015c2fd3688f154dd7d064d1e00e5484711314e9f0b3e2e863b085
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6cd997f499454e13ac4dabde7c9b3fae456372bd14cee40bac36217d9c8b4b1
+oid sha256:9e85371deea3100d2ab445c982136740c600243d9badeb6e5c72c07324d88a6c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.0,
+  "epoch": 2.6666666666666665,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 27.768,
       "eval_steps_per_second": 2.793,
       "step": 150
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 2.078125,
+      "learning_rate": 0.00019505909417784754,
+      "loss": 0.7759,
+      "step": 160
+    },
+    {
+      "epoch": 2.2666666666666666,
+      "grad_norm": 4.59375,
+      "learning_rate": 0.00019408298407861042,
+      "loss": 0.7577,
+      "step": 170
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 3.234375,
+      "learning_rate": 0.00019302184919509755,
+      "loss": 0.7745,
+      "step": 180
+    },
+    {
+      "epoch": 2.533333333333333,
+      "grad_norm": 1.796875,
+      "learning_rate": 0.0001918766484973654,
+      "loss": 0.7984,
+      "step": 190
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 1.8125,
+      "learning_rate": 0.0001906484169275263,
+      "loss": 0.8212,
+      "step": 200
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "eval_loss": 2.586805582046509,
+      "eval_runtime": 42.7073,
+      "eval_samples_per_second": 35.146,
+      "eval_steps_per_second": 3.536,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -163,7 +206,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.114462893768704e+16,
+  "total_flos": 6.819283858358272e+16,
   "train_batch_size": 5,
   "trial_name": null,
   "trial_params": null