Training in progress, epoch 1, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d8e1016a9b1bb6828135669bed415800d12ec729a55e57ed78cb1ee7ab1bbc2
+oid sha256:f64e8b6ce3e39a5e6797bf8fe4b1f46ca60c4a2c1460d772f00ecb159098f38c
 size 2682482800

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd973e6941dbfc054a82a8fc125c7daff458020cf56c2f24a45ed7a61ec17d74
+oid sha256:f33f4a02dd2da4ae6eff3580212c2a887d59573ba0130bf4d5788e5476e66d99
 size 5365108834

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08baa7817becd0350efcb73cd20230a3510c2a4c44eabb35442e644589d91b4e
+oid sha256:35d49c40f3ce3777da17a367a415379e0b695fe3b4e3bfd83e8e08a807361e43
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8196dfb311939b1d2d31afb1d2e2c773958196863e2aef7e228bd8c79258297b
+oid sha256:0b7daf508bc85526f69b8f3b71377a6a6256f8d93d4aaf541b8c9a6b631bc6c8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9972065305108946,
+  "epoch": 1.9972065305108946,
   "eval_steps": 50,
-  "global_step": 251,
+  "global_step": 502,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -82,6 +82,81 @@
       "eval_samples_per_second": 57.984,
       "eval_steps_per_second": 28.992,
       "step": 250
+    },
+    {
+      "epoch": 1.1946737848407722,
+      "grad_norm": 1.051540493965149,
+      "learning_rate": 8.804780876494024e-05,
+      "loss": 1.3707,
+      "step": 300
+    },
+    {
+      "epoch": 1.1946737848407722,
+      "eval_loss": 1.3773671388626099,
+      "eval_runtime": 14.6834,
+      "eval_samples_per_second": 57.752,
+      "eval_steps_per_second": 28.876,
+      "step": 300
+    },
+    {
+      "epoch": 1.39332050406605,
+      "grad_norm": 0.9810565710067749,
+      "learning_rate": 8.605577689243029e-05,
+      "loss": 1.331,
+      "step": 350
+    },
+    {
+      "epoch": 1.39332050406605,
+      "eval_loss": 1.33962881565094,
+      "eval_runtime": 14.6332,
+      "eval_samples_per_second": 57.95,
+      "eval_steps_per_second": 28.975,
+      "step": 350
+    },
+    {
+      "epoch": 1.5919672232913278,
+      "grad_norm": 1.0661150217056274,
+      "learning_rate": 8.406374501992032e-05,
+      "loss": 1.314,
+      "step": 400
+    },
+    {
+      "epoch": 1.5919672232913278,
+      "eval_loss": 1.3049601316452026,
+      "eval_runtime": 14.7683,
+      "eval_samples_per_second": 57.42,
+      "eval_steps_per_second": 28.71,
+      "step": 400
+    },
+    {
+      "epoch": 1.7906139425166057,
+      "grad_norm": 1.1233532428741455,
+      "learning_rate": 8.207171314741037e-05,
+      "loss": 1.2799,
+      "step": 450
+    },
+    {
+      "epoch": 1.7906139425166057,
+      "eval_loss": 1.2853434085845947,
+      "eval_runtime": 14.6881,
+      "eval_samples_per_second": 57.734,
+      "eval_steps_per_second": 28.867,
+      "step": 450
+    },
+    {
+      "epoch": 1.9892606617418833,
+      "grad_norm": 0.9072484970092773,
+      "learning_rate": 8.00796812749004e-05,
+      "loss": 1.2684,
+      "step": 500
+    },
+    {
+      "epoch": 1.9892606617418833,
+      "eval_loss": 1.2741819620132446,
+      "eval_runtime": 14.6458,
+      "eval_samples_per_second": 57.901,
+      "eval_steps_per_second": 28.95,
+      "step": 500
     }
   ],
   "logging_steps": 50,
@@ -101,7 +176,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.004589805030605e+16,
+  "total_flos": 8.013656905429811e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null