Training in progress, epoch 2, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6531ff136929ea8b6d94dfbb165131581a2ff74ef461f35b4b43c0141cb9657b
+oid sha256:34490b11fd4cbe7923634df9f619fb28255cd5ca4be8f47851b613e424fb9719
 size 2695611744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5847d96eb1458c9681ef9789a0a9c39c7dcffa10b6a0bf06cc6d997929dc0904
+oid sha256:42477444ff7806fafc89fbff44c7141e097d3d1ceba11237493438b377b733b3
 size 26261260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:838e024e0a852529a2257dc1dc52b7019dd292f53abc55b9fa61835eb1065232
+oid sha256:0d15855cc66c2961c5cc037b181eb659abb2ac26d92d4c28480e27683e47e34e
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bca4dbe650e04bc8012dd3f1938dfb2a637329721abd75c3bd59d28a64007b54
+oid sha256:0e8b7bfccb9c07860bceffabef3a52060cc451a19d3abd90d284c09f7120dba6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0,
+  "epoch": 2.0,
   "eval_steps": 10,
-  "global_step": 129,
+  "global_step": 258,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -175,6 +175,188 @@
       "eval_samples_per_second": 21.996,
       "eval_steps_per_second": 5.499,
       "step": 120
+    },
+    {
+      "epoch": 1.0078086871644705,
+      "grad_norm": 0.7562536597251892,
+      "learning_rate": 8.984375e-05,
+      "loss": 1.6984,
+      "step": 130
+    },
+    {
+      "epoch": 1.0078086871644705,
+      "eval_runtime": 19.5758,
+      "eval_samples_per_second": 22.068,
+      "eval_steps_per_second": 5.517,
+      "step": 130
+    },
+    {
+      "epoch": 1.0858955588091752,
+      "grad_norm": 0.8962981700897217,
+      "learning_rate": 8.90625e-05,
+      "loss": 1.8936,
+      "step": 140
+    },
+    {
+      "epoch": 1.0858955588091752,
+      "eval_runtime": 19.608,
+      "eval_samples_per_second": 22.032,
+      "eval_steps_per_second": 5.508,
+      "step": 140
+    },
+    {
+      "epoch": 1.16398243045388,
+      "grad_norm": 0.513067901134491,
+      "learning_rate": 8.828125000000001e-05,
+      "loss": 1.8596,
+      "step": 150
+    },
+    {
+      "epoch": 1.16398243045388,
+      "eval_runtime": 19.6282,
+      "eval_samples_per_second": 22.009,
+      "eval_steps_per_second": 5.502,
+      "step": 150
+    },
+    {
+      "epoch": 1.2420693020985847,
+      "grad_norm": 1.018214225769043,
+      "learning_rate": 8.75e-05,
+      "loss": 1.9079,
+      "step": 160
+    },
+    {
+      "epoch": 1.2420693020985847,
+      "eval_runtime": 19.6252,
+      "eval_samples_per_second": 22.013,
+      "eval_steps_per_second": 5.503,
+      "step": 160
+    },
+    {
+      "epoch": 1.3201561737432894,
+      "grad_norm": 0.7686395049095154,
+      "learning_rate": 8.671875e-05,
+      "loss": 1.9337,
+      "step": 170
+    },
+    {
+      "epoch": 1.3201561737432894,
+      "eval_runtime": 19.6277,
+      "eval_samples_per_second": 22.01,
+      "eval_steps_per_second": 5.502,
+      "step": 170
+    },
+    {
+      "epoch": 1.3982430453879942,
+      "grad_norm": 0.26993170380592346,
+      "learning_rate": 8.593750000000001e-05,
+      "loss": 1.8956,
+      "step": 180
+    },
+    {
+      "epoch": 1.3982430453879942,
+      "eval_runtime": 19.6507,
+      "eval_samples_per_second": 21.984,
+      "eval_steps_per_second": 5.496,
+      "step": 180
+    },
+    {
+      "epoch": 1.476329917032699,
+      "grad_norm": 0.995215892791748,
+      "learning_rate": 8.515625e-05,
+      "loss": 1.8703,
+      "step": 190
+    },
+    {
+      "epoch": 1.476329917032699,
+      "eval_runtime": 19.6347,
+      "eval_samples_per_second": 22.002,
+      "eval_steps_per_second": 5.5,
+      "step": 190
+    },
+    {
+      "epoch": 1.5544167886774036,
+      "grad_norm": 1.6944684982299805,
+      "learning_rate": 8.4375e-05,
+      "loss": 1.925,
+      "step": 200
+    },
+    {
+      "epoch": 1.5544167886774036,
+      "eval_runtime": 19.6152,
+      "eval_samples_per_second": 22.024,
+      "eval_steps_per_second": 5.506,
+      "step": 200
+    },
+    {
+      "epoch": 1.6325036603221084,
+      "grad_norm": 1.6777361631393433,
+      "learning_rate": 8.359375000000001e-05,
+      "loss": 1.8993,
+      "step": 210
+    },
+    {
+      "epoch": 1.6325036603221084,
+      "eval_runtime": 19.6141,
+      "eval_samples_per_second": 22.025,
+      "eval_steps_per_second": 5.506,
+      "step": 210
+    },
+    {
+      "epoch": 1.710590531966813,
+      "grad_norm": 1.1011719703674316,
+      "learning_rate": 8.28125e-05,
+      "loss": 1.8768,
+      "step": 220
+    },
+    {
+      "epoch": 1.710590531966813,
+      "eval_runtime": 19.6432,
+      "eval_samples_per_second": 21.992,
+      "eval_steps_per_second": 5.498,
+      "step": 220
+    },
+    {
+      "epoch": 1.7886774036115178,
+      "grad_norm": 2.650319814682007,
+      "learning_rate": 8.203125e-05,
+      "loss": 1.8895,
+      "step": 230
+    },
+    {
+      "epoch": 1.7886774036115178,
+      "eval_runtime": 19.6217,
+      "eval_samples_per_second": 22.016,
+      "eval_steps_per_second": 5.504,
+      "step": 230
+    },
+    {
+      "epoch": 1.8667642752562226,
+      "grad_norm": 1.122077226638794,
+      "learning_rate": 8.125000000000001e-05,
+      "loss": 1.8866,
+      "step": 240
+    },
+    {
+      "epoch": 1.8667642752562226,
+      "eval_runtime": 19.6566,
+      "eval_samples_per_second": 21.977,
+      "eval_steps_per_second": 5.494,
+      "step": 240
+    },
+    {
+      "epoch": 1.9448511469009273,
+      "grad_norm": 0.9412140846252441,
+      "learning_rate": 8.046875e-05,
+      "loss": 1.8959,
+      "step": 250
+    },
+    {
+      "epoch": 1.9448511469009273,
+      "eval_runtime": 19.6565,
+      "eval_samples_per_second": 21.977,
+      "eval_steps_per_second": 5.494,
+      "step": 250
     }
   ],
   "logging_steps": 10,