Training in progress, step 40, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c58843ce054ff5e21298dea3c5d5e5c129a92e1880c1960584e9f689cad25fdf
+oid sha256:160db84884c852936290c2dbabae2e7aef7f29215bea95251f3d7c6279739be7
 size 91951912

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24aa5f3b72ad380e256c083f5f9371f8cfb26a73ec8a1c9b48e511e8aa2db999
+oid sha256:871faa733ae16c56f62ff4acb9dc36002b66d420908dd14f8542137ab911d7ef
 size 183993547

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8e2011629d8bed3ef560fa11175cac55684c4e12a72634bb24abf767b6c7399
+oid sha256:718a0f3db00824213036a2c0441849791319b7d9cf189065873bb26a7020738e
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93e1ac18ac1a54b596386c66a16892db4ef550952673522950938aa63c716ef9
+oid sha256:78d8446916771bdbc3272fb5483d27a47f792f342be43af6bfbcc122b7703745
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003,
+  "epoch": 0.004,
   "eval_steps": 10,
-  "global_step": 30,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -242,6 +242,84 @@
       "eval_samples_per_second": 14.699,
       "eval_steps_per_second": 1.837,
       "step": 30
+    },
+    {
+      "epoch": 0.0031,
+      "grad_norm": 2.902653694152832,
+      "learning_rate": 0.00030000000000000003,
+      "loss": 19.6354,
+      "step": 31
+    },
+    {
+      "epoch": 0.0032,
+      "grad_norm": 2.723034620285034,
+      "learning_rate": 0.00031,
+      "loss": 18.3838,
+      "step": 32
+    },
+    {
+      "epoch": 0.0033,
+      "grad_norm": 2.559993267059326,
+      "learning_rate": 0.00032,
+      "loss": 16.345,
+      "step": 33
+    },
+    {
+      "epoch": 0.0034,
+      "grad_norm": 2.283393144607544,
+      "learning_rate": 0.00033,
+      "loss": 14.2652,
+      "step": 34
+    },
+    {
+      "epoch": 0.0035,
+      "grad_norm": 2.1815197467803955,
+      "learning_rate": 0.00033999999999999997,
+      "loss": 14.0831,
+      "step": 35
+    },
+    {
+      "epoch": 0.0036,
+      "grad_norm": 2.018310308456421,
+      "learning_rate": 0.00035,
+      "loss": 12.7781,
+      "step": 36
+    },
+    {
+      "epoch": 0.0037,
+      "grad_norm": 1.862168550491333,
+      "learning_rate": 0.00035999999999999997,
+      "loss": 11.4392,
+      "step": 37
+    },
+    {
+      "epoch": 0.0038,
+      "grad_norm": 1.762819528579712,
+      "learning_rate": 0.00037,
+      "loss": 10.6711,
+      "step": 38
+    },
+    {
+      "epoch": 0.0039,
+      "grad_norm": 1.6565489768981934,
+      "learning_rate": 0.00038,
+      "loss": 9.3263,
+      "step": 39
+    },
+    {
+      "epoch": 0.004,
+      "grad_norm": 1.545681118965149,
+      "learning_rate": 0.00039000000000000005,
+      "loss": 9.0413,
+      "step": 40
+    },
+    {
+      "epoch": 0.004,
+      "eval_loss": 0.9703376889228821,
+      "eval_runtime": 681.7846,
+      "eval_samples_per_second": 14.667,
+      "eval_steps_per_second": 1.833,
+      "step": 40
     }
   ],
   "logging_steps": 1,