Training in progress, step 60, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5edb98a1e6c523dcd5a3c5cf784f7b65a32ca68720e44b415cbd6e8cffabaab7
+oid sha256:2a8ac80e0d61cf456d72737d89bb1c469c41be9cddc5d5b79f1386e89c845e9e
 size 91951912

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79058ecee9f122e8a7141d1a9505f3c5fe3a358112e64619fd215c1937bbe280
+oid sha256:e7d79905e4e06711ab933d9e5514af128e4c7733ef6c234b0188b59a5450ace8
 size 183993547

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01f9a0f7843a37be87edd23f4e88aa93b38b95cc2c07503eeb1cf2e4632453a2
+oid sha256:f196323d7423b60f8e4ceb7dbf8715ee326c0d068e5ff164f13c63b279b9f1a0
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c414e5d294244b6e3f30629a4eba6627304506f72ac598738943e55c96b2fce
+oid sha256:b148ddbe2b5b3f44d0a202131520ae8c1b9f366b630fec86449c6dc228c6c8a7
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005,
+  "epoch": 0.006,
   "eval_steps": 10,
-  "global_step": 50,
+  "global_step": 60,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -398,6 +398,84 @@
       "eval_samples_per_second": 14.691,
       "eval_steps_per_second": 1.836,
       "step": 50
+    },
+    {
+      "epoch": 0.0051,
+      "grad_norm": 1.5408843755722046,
+      "learning_rate": 0.0005,
+      "loss": 3.7493,
+      "step": 51
+    },
+    {
+      "epoch": 0.0052,
+      "grad_norm": 0.7898032069206238,
+      "learning_rate": 0.00051,
+      "loss": 2.5679,
+      "step": 52
+    },
+    {
+      "epoch": 0.0053,
+      "grad_norm": 0.7600494027137756,
+      "learning_rate": 0.0005200000000000001,
+      "loss": 2.116,
+      "step": 53
+    },
+    {
+      "epoch": 0.0054,
+      "grad_norm": 0.6847724318504333,
+      "learning_rate": 0.00053,
+      "loss": 1.9753,
+      "step": 54
+    },
+    {
+      "epoch": 0.0055,
+      "grad_norm": 0.9391168355941772,
+      "learning_rate": 0.00054,
+      "loss": 2.6345,
+      "step": 55
+    },
+    {
+      "epoch": 0.0056,
+      "grad_norm": 0.614797830581665,
+      "learning_rate": 0.0005499999999999999,
+      "loss": 1.4403,
+      "step": 56
+    },
+    {
+      "epoch": 0.0057,
+      "grad_norm": 0.6510812044143677,
+      "learning_rate": 0.0005600000000000001,
+      "loss": 1.4256,
+      "step": 57
+    },
+    {
+      "epoch": 0.0058,
+      "grad_norm": 0.5823825001716614,
+      "learning_rate": 0.00057,
+      "loss": 1.2711,
+      "step": 58
+    },
+    {
+      "epoch": 0.0059,
+      "grad_norm": 1.0760960578918457,
+      "learning_rate": 0.00058,
+      "loss": 2.4494,
+      "step": 59
+    },
+    {
+      "epoch": 0.006,
+      "grad_norm": 0.6940433382987976,
+      "learning_rate": 0.00059,
+      "loss": 1.2022,
+      "step": 60
+    },
+    {
+      "epoch": 0.006,
+      "eval_loss": 0.11387959867715836,
+      "eval_runtime": 680.3956,
+      "eval_samples_per_second": 14.697,
+      "eval_steps_per_second": 1.837,
+      "step": 60
     }
   ],
   "logging_steps": 1,