Training in progress, step 200, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a32d2c3a667587764cd9ca5d6d70a240736bf426d6475dac4043133fa73816ee
+oid sha256:0e6466b58c3c120a943d635b9b9f77c78317c742d1be703c5a32a4b57e4ec1c8
 size 355970836

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd98378eb1df249c95152f56a7c980be9183dd9e5ac769e4f33b80952e554f55
+oid sha256:73929ca6199d0cd5698949579f301ee09e22518ce3c78b1528bb2ba92bd5f78f
 size 712036922

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e392bc84f8761c1cb361bf95966bfb38a86990c20193cb6f07afc3e9b98a5dd
+oid sha256:02ac934b04f9ad30a9947051ab49a9c4b8fcfbf28262f73cd84f8b6fe5cdc61a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aacb2caac6c123a2e842fada3eab2f7441181ca135f4cd4779f74c20a10ad6c1
+oid sha256:e868db493f34528bd828066f7bfb20c4fcf4eb5967587ac96dfd619d77eeab66
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0027131336014813707,
+  "epoch": 0.0054262672029627415,
   "eval_steps": 500,
-  "global_step": 100,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -77,6 +77,76 @@
       "learning_rate": 1.76e-05,
       "loss": 37.2538,
       "step": 100
+    },
+    {
+      "epoch": 0.002984446961629508,
+      "grad_norm": 78771.6875,
+      "learning_rate": 1.9600000000000002e-05,
+      "loss": 36.8398,
+      "step": 110
+    },
+    {
+      "epoch": 0.0032557603217776452,
+      "grad_norm": 4261.8388671875,
+      "learning_rate": 2.16e-05,
+      "loss": 38.1147,
+      "step": 120
+    },
+    {
+      "epoch": 0.0035270736819257823,
+      "grad_norm": 354.98797607421875,
+      "learning_rate": 2.36e-05,
+      "loss": 40.2607,
+      "step": 130
+    },
+    {
+      "epoch": 0.0037983870420739193,
+      "grad_norm": 2892.681640625,
+      "learning_rate": 2.5600000000000002e-05,
+      "loss": 43.2013,
+      "step": 140
+    },
+    {
+      "epoch": 0.004069700402222057,
+      "grad_norm": 1937.0869140625,
+      "learning_rate": 2.7600000000000003e-05,
+      "loss": 36.9207,
+      "step": 150
+    },
+    {
+      "epoch": 0.004341013762370193,
+      "grad_norm": 2947.12939453125,
+      "learning_rate": 2.96e-05,
+      "loss": 37.1433,
+      "step": 160
+    },
+    {
+      "epoch": 0.004612327122518331,
+      "grad_norm": 69275.578125,
+      "learning_rate": 3.16e-05,
+      "loss": 35.2396,
+      "step": 170
+    },
+    {
+      "epoch": 0.004883640482666467,
+      "grad_norm": 113316.1328125,
+      "learning_rate": 3.3400000000000005e-05,
+      "loss": 52.4227,
+      "step": 180
+    },
+    {
+      "epoch": 0.005154953842814605,
+      "grad_norm": 21579.859375,
+      "learning_rate": 3.54e-05,
+      "loss": 44.2034,
+      "step": 190
+    },
+    {
+      "epoch": 0.0054262672029627415,
+      "grad_norm": 23244.189453125,
+      "learning_rate": 3.74e-05,
+      "loss": 48.1572,
+      "step": 200
     }
   ],
   "logging_steps": 10,