Training in progress, step 26000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfc5c32d531b4d03970087391e1f7ca6763b9d1de362d6cda421b7d124b979c8
+oid sha256:868ebbe6082f4ffc7e26ac72b39865598fd064bb047080552522aaec1058ad6e
 size 496262784

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:baff61bb16847080902923a972f48196a5da070aa7a9295b3b6f30d9c6da65c5
+oid sha256:958faabaf0650341769a72f6210e71dac68bc179b0667c9cbcc58bde08e00373
 size 992621963

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:707f3295d65fc2b08af5a95df451c0c1f230854850d6c8193dd0137a6c028a4e
+oid sha256:df2f80d39b1989ec660dedb19baf83fbbecae216591a339f013067bf7a57f050
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acdbaf996d8220fb05cb901198d39146ebe82d7a748d641503b0d9a4f0d91bc3
+oid sha256:56ea06e88c8e616d19485413e7e9adaf9b94b71f0e4fc7adfe79acd6535722fe
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.48,
+  "epoch": 0.52,
   "eval_steps": 1000,
-  "global_step": 24000,
+  "global_step": 26000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1904,6 +1904,164 @@
       "eval_samples_per_second": 325.269,
       "eval_steps_per_second": 20.445,
       "step": 24000
+    },
+    {
+      "epoch": 0.482,
+      "grad_norm": 338.5876770019531,
+      "learning_rate": 0.0003184408911597519,
+      "loss": 7.839384155273438,
+      "step": 24100
+    },
+    {
+      "epoch": 0.484,
+      "grad_norm": 79.88603210449219,
+      "learning_rate": 0.0003165534852388384,
+      "loss": 7.44333251953125,
+      "step": 24200
+    },
+    {
+      "epoch": 0.486,
+      "grad_norm": 32.77883529663086,
+      "learning_rate": 0.0003146654218759499,
+      "loss": 7.235584106445312,
+      "step": 24300
+    },
+    {
+      "epoch": 0.488,
+      "grad_norm": 27.993099212646484,
+      "learning_rate": 0.0003127767760578392,
+      "loss": 7.177199096679687,
+      "step": 24400
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 15.215092658996582,
+      "learning_rate": 0.000310887622794392,
+      "loss": 7.115394287109375,
+      "step": 24500
+    },
+    {
+      "epoch": 0.492,
+      "grad_norm": 12.316529273986816,
+      "learning_rate": 0.00030899803711564806,
+      "loss": 6.990827026367188,
+      "step": 24600
+    },
+    {
+      "epoch": 0.494,
+      "grad_norm": 2.696770191192627,
+      "learning_rate": 0.0003071080940688207,
+      "loss": 7.0589227294921875,
+      "step": 24700
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 48.15589141845703,
+      "learning_rate": 0.0003052178687153168,
+      "loss": 7.067171020507812,
+      "step": 24800
+    },
+    {
+      "epoch": 0.498,
+      "grad_norm": 28.01230239868164,
+      "learning_rate": 0.0003033274361277553,
+      "loss": 7.030769653320313,
+      "step": 24900
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 69.79560852050781,
+      "learning_rate": 0.0003014368713869857,
+      "loss": 6.974198608398438,
+      "step": 25000
+    },
+    {
+      "epoch": 0.5,
+      "eval_accuracy": 0.09623723724632026,
+      "eval_loss": 6.917368412017822,
+      "eval_runtime": 6.0867,
+      "eval_samples_per_second": 318.891,
+      "eval_steps_per_second": 20.044,
+      "step": 25000
+    },
+    {
+      "epoch": 0.502,
+      "grad_norm": 42.4299201965332,
+      "learning_rate": 0.00029954624957910595,
+      "loss": 6.993025512695312,
+      "step": 25100
+    },
+    {
+      "epoch": 0.504,
+      "grad_norm": 20.528335571289062,
+      "learning_rate": 0.0002976556457924811,
+      "loss": 7.020432739257813,
+      "step": 25200
+    },
+    {
+      "epoch": 0.506,
+      "grad_norm": 42.26169204711914,
+      "learning_rate": 0.0002957651351147596,
+      "loss": 6.934894409179687,
+      "step": 25300
+    },
+    {
+      "epoch": 0.508,
+      "grad_norm": 3.344475507736206,
+      "learning_rate": 0.0002938747926298927,
+      "loss": 6.941484375,
+      "step": 25400
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 64.28266906738281,
+      "learning_rate": 0.0002919846934151513,
+      "loss": 7.314700317382813,
+      "step": 25500
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 29.82670783996582,
+      "learning_rate": 0.00029009491253814457,
+      "loss": 7.119804077148437,
+      "step": 25600
+    },
+    {
+      "epoch": 0.514,
+      "grad_norm": 59.44496536254883,
+      "learning_rate": 0.0002882055250538384,
+      "loss": 7.006104736328125,
+      "step": 25700
+    },
+    {
+      "epoch": 0.516,
+      "grad_norm": 42.77421569824219,
+      "learning_rate": 0.00028631660600157493,
+      "loss": 6.991202392578125,
+      "step": 25800
+    },
+    {
+      "epoch": 0.518,
+      "grad_norm": 14.600953102111816,
+      "learning_rate": 0.0002844282304020917,
+      "loss": 6.969422607421875,
+      "step": 25900
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 77.17425537109375,
+      "learning_rate": 0.00028254047325454234,
+      "loss": 7.046774291992188,
+      "step": 26000
+    },
+    {
+      "epoch": 0.52,
+      "eval_accuracy": 0.06708366478432748,
+      "eval_loss": 7.517740249633789,
+      "eval_runtime": 5.7572,
+      "eval_samples_per_second": 337.143,
+      "eval_steps_per_second": 21.191,
+      "step": 26000
     }
   ],
   "logging_steps": 100,
@@ -1923,7 +2081,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.5252105216e+17,
+  "total_flos": 8.1523113984e+17,
   "train_batch_size": 120,
   "trial_name": null,
   "trial_params": null