Training in progress, step 120, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:340c0a0821f363d717e83f3e5f6e7ea2bafdce4ef706b3825ab908120d673bec
+oid sha256:4e65a61da3bd59857bc61ebd07e726758d8f85f0c3bbf9a6bdfafa5218f0a6c3
 size 91951912

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91962936c531b7b7ddf6d02a84ba8b22196c5d8879b878e3523b18b244be6ac7
+oid sha256:665e7c098b20618c3e078ad86acab2e0ca25d1467a8d0e2112c68af547b92299
 size 183993547

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1255b82ec9f462fef6f8c2f4a8ee876c4b6d998a53c99546a4eddcc1aabaefc7
+oid sha256:236304ae89e49aae8260113165ee63419b9b745f79120014328a7fa31ed79b42
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bed0fc10cc2a630bca255800a674f5add6e38356fc5bd269eec0b0845d932a5e
+oid sha256:d352eeae2aa15ed4d011e01fe52a140d1d472b101b8457914fdee010588d6f43
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.011,
+  "epoch": 0.012,
   "eval_steps": 10,
-  "global_step": 110,
+  "global_step": 120,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -866,6 +866,84 @@
       "eval_samples_per_second": 14.704,
       "eval_steps_per_second": 1.838,
       "step": 110
+    },
+    {
+      "epoch": 0.0111,
+      "grad_norm": 0.035101134330034256,
+      "learning_rate": 0.0010999999999999998,
+      "loss": 0.0292,
+      "step": 111
+    },
+    {
+      "epoch": 0.0112,
+      "grad_norm": 0.03888938948512077,
+      "learning_rate": 0.00111,
+      "loss": 0.0291,
+      "step": 112
+    },
+    {
+      "epoch": 0.0113,
+      "grad_norm": 0.027459941804409027,
+      "learning_rate": 0.0011200000000000001,
+      "loss": 0.0232,
+      "step": 113
+    },
+    {
+      "epoch": 0.0114,
+      "grad_norm": 0.04769216105341911,
+      "learning_rate": 0.00113,
+      "loss": 0.0337,
+      "step": 114
+    },
+    {
+      "epoch": 0.0115,
+      "grad_norm": 0.024265864863991737,
+      "learning_rate": 0.00114,
+      "loss": 0.0233,
+      "step": 115
+    },
+    {
+      "epoch": 0.0116,
+      "grad_norm": 0.07471495121717453,
+      "learning_rate": 0.0011500000000000002,
+      "loss": 0.039,
+      "step": 116
+    },
+    {
+      "epoch": 0.0117,
+      "grad_norm": 0.03743023797869682,
+      "learning_rate": 0.00116,
+      "loss": 0.0291,
+      "step": 117
+    },
+    {
+      "epoch": 0.0118,
+      "grad_norm": 0.025691425427794456,
+      "learning_rate": 0.00117,
+      "loss": 0.024,
+      "step": 118
+    },
+    {
+      "epoch": 0.0119,
+      "grad_norm": 0.02821824699640274,
+      "learning_rate": 0.00118,
+      "loss": 0.0245,
+      "step": 119
+    },
+    {
+      "epoch": 0.012,
+      "grad_norm": 0.027008380740880966,
+      "learning_rate": 0.00119,
+      "loss": 0.0271,
+      "step": 120
+    },
+    {
+      "epoch": 0.012,
+      "eval_loss": 0.0045553590171039104,
+      "eval_runtime": 685.7922,
+      "eval_samples_per_second": 14.582,
+      "eval_steps_per_second": 1.823,
+      "step": 120
     }
   ],
   "logging_steps": 1,