Training in progress, step 30, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08b1a07f0e1de978b319a287a04e2d899a4a6520e9fbcd1b41b5785d0750b01e
+oid sha256:c58843ce054ff5e21298dea3c5d5e5c129a92e1880c1960584e9f689cad25fdf
 size 91951912

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a96e33b51a92420e5fbe54d9368081919b1b7075648b2a9576f2232ef1274d8
+oid sha256:24aa5f3b72ad380e256c083f5f9371f8cfb26a73ec8a1c9b48e511e8aa2db999
 size 183993547

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4a9f217e852f439efa6bd32fde98d6867f11aa6ea13ddc021ba10af6a0b0934
+oid sha256:a8e2011629d8bed3ef560fa11175cac55684c4e12a72634bb24abf767b6c7399
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f6206e0011d397a959aa5be7ba1e8e6b2e2d2e821a6b9b129b1c771bca053e7
+oid sha256:93e1ac18ac1a54b596386c66a16892db4ef550952673522950938aa63c716ef9
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002,
+  "epoch": 0.003,
   "eval_steps": 10,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -164,6 +164,84 @@
       "eval_samples_per_second": 14.714,
       "eval_steps_per_second": 1.839,
       "step": 20
+    },
+    {
+      "epoch": 0.0021,
+      "grad_norm": 5.3365912437438965,
+      "learning_rate": 0.0002,
+      "loss": 39.7964,
+      "step": 21
+    },
+    {
+      "epoch": 0.0022,
+      "grad_norm": 5.166492462158203,
+      "learning_rate": 0.00021000000000000004,
+      "loss": 37.9665,
+      "step": 22
+    },
+    {
+      "epoch": 0.0023,
+      "grad_norm": 4.789157867431641,
+      "learning_rate": 0.00022,
+      "loss": 35.5756,
+      "step": 23
+    },
+    {
+      "epoch": 0.0024,
+      "grad_norm": 4.50107479095459,
+      "learning_rate": 0.00022999999999999998,
+      "loss": 33.2697,
+      "step": 24
+    },
+    {
+      "epoch": 0.0025,
+      "grad_norm": 4.265627384185791,
+      "learning_rate": 0.00024,
+      "loss": 31.4949,
+      "step": 25
+    },
+    {
+      "epoch": 0.0026,
+      "grad_norm": 4.027210235595703,
+      "learning_rate": 0.00025,
+      "loss": 28.0505,
+      "step": 26
+    },
+    {
+      "epoch": 0.0027,
+      "grad_norm": 3.928957223892212,
+      "learning_rate": 0.00026000000000000003,
+      "loss": 26.2355,
+      "step": 27
+    },
+    {
+      "epoch": 0.0028,
+      "grad_norm": 3.5308196544647217,
+      "learning_rate": 0.00027,
+      "loss": 24.1822,
+      "step": 28
+    },
+    {
+      "epoch": 0.0029,
+      "grad_norm": 3.3050384521484375,
+      "learning_rate": 0.00028000000000000003,
+      "loss": 23.0633,
+      "step": 29
+    },
+    {
+      "epoch": 0.003,
+      "grad_norm": 3.0656802654266357,
+      "learning_rate": 0.00029,
+      "loss": 20.7796,
+      "step": 30
+    },
+    {
+      "epoch": 0.003,
+      "eval_loss": 2.453228235244751,
+      "eval_runtime": 680.3163,
+      "eval_samples_per_second": 14.699,
+      "eval_steps_per_second": 1.837,
+      "step": 30
     }
   ],
   "logging_steps": 1,