Training in progress, step 100, checkpoint

last-checkpoint/model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d5991d4ae0fc94498a8143cbe4998a750029e51f58a03fa7d87196dd90323f4
+oid sha256:c181850783b51fc1b54edd4fa27053218e7bd9412a9a06d8d85c03b4c0b31b6a
 size 4943178720

last-checkpoint/model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab0adf5e4a12d0566d1af6170cc37600bf554158b9960ce331bbf55161988fd1
+oid sha256:b62ab75bdfa82032c63e0d69f29df189a216779f0cdc96d4e685ab22ee1e1415
 size 4999819336

last-checkpoint/model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c1d5eeee2a3d4aff325f9aa208ce5126187018a83ea8147fea0efdee4117a54
+oid sha256:b1685fadb7da58fee532f9124714120dcf3943170b9ecefcae04d272e26d798d
 size 4540532728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:541203c5d442071eaec535dae26efc2cf78294860f7e1ac99066f4215885bd58
+oid sha256:46b6cae90969af499a1a0e72b399ed2f5300b48f0f17bd9cf7dc83d7d82bed12
 size 14710155092

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:455445cc351d1d9c0932fce6221afb99c553d40bbefe6e459ef4b63ef6e54132
+oid sha256:9420ac59722557c2d75561b7a80141668226ad32b0226580eab59c780161b06f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3353489b38799fd56e115bb7a4e2a7a61242a09d303dca9e218c08878b9b8728
+oid sha256:aeada689887050f844873eed093c0e42e31037d558c794e13e2aaf05bbc18b5b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.11848341232227488,
+  "epoch": 0.23696682464454977,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 13.6,
       "eval_steps_per_second": 6.804,
       "step": 50
+    },
+    {
+      "epoch": 0.14218009478672985,
+      "grad_norm": 43.25,
+      "learning_rate": 9.6e-05,
+      "loss": 3.2101,
+      "step": 60
+    },
+    {
+      "epoch": 0.16587677725118483,
+      "grad_norm": 55.5,
+      "learning_rate": 0.00011200000000000001,
+      "loss": 3.2406,
+      "step": 70
+    },
+    {
+      "epoch": 0.1895734597156398,
+      "grad_norm": 49.25,
+      "learning_rate": 0.00012800000000000002,
+      "loss": 3.4937,
+      "step": 80
+    },
+    {
+      "epoch": 0.2132701421800948,
+      "grad_norm": 808.0,
+      "learning_rate": 0.000144,
+      "loss": 3.9683,
+      "step": 90
+    },
+    {
+      "epoch": 0.23696682464454977,
+      "grad_norm": 201.0,
+      "learning_rate": 0.00016,
+      "loss": 4.5857,
+      "step": 100
+    },
+    {
+      "epoch": 0.23696682464454977,
+      "eval_loss": 4.856403827667236,
+      "eval_runtime": 110.2664,
+      "eval_samples_per_second": 13.612,
+      "eval_steps_per_second": 6.811,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8737589192294400.0,
+  "total_flos": 1.74751783845888e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null