Training in progress, step 4000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:087a9502c82c5c47cb21b72b70c5ccef09dcdc1199ed97b71e3e6ce85dd4649f
+oid sha256:2c7a9efb55a7cc3b4432f226863fe6ef1c9292f3ad0f7c0ca92fab5349a572f5
 size 529337896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b4b223be013480e5550b7c0fbb290de78633af3e1731c52d8d7d6ef8a61a635
+oid sha256:4464c4cbdf59560aaae68cbe3fba5acc3e81f456f12b51fda7e20de6eb07052a
 size 871247243

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14cd4a8cf54ce87e9e7818ae50060fa501ea05e8685c2025ab631bfde31c87cf
+oid sha256:93a7a87e66fdab18edc7df0621c2a005fd54541ab1c68bc3e038e8b969d2fabe
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b716fb1dcbc77ddc6a0ae7c4c98d559e36f1986fff006ef6982bd75247833235
+oid sha256:76cf98a8cde877f1e49a9e4b884c4dce3d51bb4035429d464e74acc35ddca024
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04,
+  "epoch": 0.08,
   "eval_steps": 1000,
-  "global_step": 2000,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -166,6 +166,164 @@
       "eval_samples_per_second": 84.549,
       "eval_steps_per_second": 0.676,
       "step": 2000
+    },
+    {
+      "epoch": 0.042,
+      "grad_norm": 0.3013302683830261,
+      "learning_rate": 0.0016792,
+      "loss": 4.1191,
+      "step": 2100
+    },
+    {
+      "epoch": 0.044,
+      "grad_norm": 0.25836440920829773,
+      "learning_rate": 0.0017592,
+      "loss": 4.075,
+      "step": 2200
+    },
+    {
+      "epoch": 0.046,
+      "grad_norm": 0.2489597499370575,
+      "learning_rate": 0.0018392,
+      "loss": 4.0824,
+      "step": 2300
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 0.24732087552547455,
+      "learning_rate": 0.0019192,
+      "loss": 4.0533,
+      "step": 2400
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.2429002970457077,
+      "learning_rate": 0.0019992,
+      "loss": 4.0472,
+      "step": 2500
+    },
+    {
+      "epoch": 0.052,
+      "grad_norm": 0.21534161269664764,
+      "learning_rate": 0.001999978563623903,
+      "loss": 4.0063,
+      "step": 2600
+    },
+    {
+      "epoch": 0.054,
+      "grad_norm": 0.2244805246591568,
+      "learning_rate": 0.0019999133871331223,
+      "loss": 4.0074,
+      "step": 2700
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 0.1999787837266922,
+      "learning_rate": 0.0019998044711915177,
+      "loss": 3.9708,
+      "step": 2800
+    },
+    {
+      "epoch": 0.058,
+      "grad_norm": 0.19969643652439117,
+      "learning_rate": 0.0019996518205634257,
+      "loss": 3.9525,
+      "step": 2900
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.21098633110523224,
+      "learning_rate": 0.0019994554419262797,
+      "loss": 3.9491,
+      "step": 3000
+    },
+    {
+      "epoch": 0.06,
+      "eval_accuracy": 0.324146771037182,
+      "eval_loss": 3.9009768962860107,
+      "eval_runtime": 18.6503,
+      "eval_samples_per_second": 53.618,
+      "eval_steps_per_second": 0.429,
+      "step": 3000
+    },
+    {
+      "epoch": 0.062,
+      "grad_norm": 0.1954544633626938,
+      "learning_rate": 0.001999215343870317,
+      "loss": 3.942,
+      "step": 3100
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.19358158111572266,
+      "learning_rate": 0.0019989315368982054,
+      "loss": 3.9159,
+      "step": 3200
+    },
+    {
+      "epoch": 0.066,
+      "grad_norm": 0.18568383157253265,
+      "learning_rate": 0.0019986040334245797,
+      "loss": 3.8959,
+      "step": 3300
+    },
+    {
+      "epoch": 0.068,
+      "grad_norm": 0.1798350065946579,
+      "learning_rate": 0.001998232847775504,
+      "loss": 3.9035,
+      "step": 3400
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.18326053023338318,
+      "learning_rate": 0.0019978179961878404,
+      "loss": 3.8771,
+      "step": 3500
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 0.1763591170310974,
+      "learning_rate": 0.001997359496808541,
+      "loss": 3.8714,
+      "step": 3600
+    },
+    {
+      "epoch": 0.074,
+      "grad_norm": 0.16502562165260315,
+      "learning_rate": 0.001996857369693855,
+      "loss": 3.8516,
+      "step": 3700
+    },
+    {
+      "epoch": 0.076,
+      "grad_norm": 0.18450422585010529,
+      "learning_rate": 0.0019963116368084486,
+      "loss": 3.8573,
+      "step": 3800
+    },
+    {
+      "epoch": 0.078,
+      "grad_norm": 0.1750190556049347,
+      "learning_rate": 0.001995722322024446,
+      "loss": 3.8403,
+      "step": 3900
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.1842149794101715,
+      "learning_rate": 0.001995089451120385,
+      "loss": 3.8158,
+      "step": 4000
+    },
+    {
+      "epoch": 0.08,
+      "eval_accuracy": 0.3340352250489237,
+      "eval_loss": 3.7926738262176514,
+      "eval_runtime": 12.3279,
+      "eval_samples_per_second": 81.117,
+      "eval_steps_per_second": 0.649,
+      "step": 4000
     }
   ],
   "logging_steps": 100,