Training in progress, step 300, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eff5893f6d1018c76da56d8c4a5822e53399dec8cbf09c3f35c6520dd57fee7a
+oid sha256:ba8406c53f83c09c1ffeabb8ce1224cbfb422c48a8d00576b75192664a252c36
 size 1235573136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ccf1805134bd0c674a65a5ac91541131c5ca34d46b4d69f086cda162433a665
+oid sha256:8a0eee39df69ccbd8f983b1f8a785ab0e689171b4e4bf4b721400c5924aa6fe6
 size 2471218763

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e8bef6dda512071503ea3bab68f0960919f4ba9156b465cc1853aaa448a81f7
+oid sha256:b31b319d83cac2dd433a790a8abad45ac5c816140a98898786a198f16bd883cd
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03d14372590aaa8a694124e857b900ce7df2b5fee119f58bc35688c4616f5961
+oid sha256:9cf04c7f94b59cd606c42cf0fc828e78ab899584bb7bbb628645ada4c3c807cf
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004,
+  "epoch": 0.006,
   "eval_steps": 500,
-  "global_step": 200,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -148,6 +148,76 @@
       "learning_rate": 0.0002994048096192384,
       "loss": 9.44781723022461,
       "step": 200
+    },
+    {
+      "epoch": 0.0042,
+      "grad_norm": 1.9302258491516113,
+      "learning_rate": 0.0002993446893787575,
+      "loss": 11.585807800292969,
+      "step": 210
+    },
+    {
+      "epoch": 0.0044,
+      "grad_norm": 1.4165903329849243,
+      "learning_rate": 0.0002992845691382765,
+      "loss": 10.411253356933594,
+      "step": 220
+    },
+    {
+      "epoch": 0.0046,
+      "grad_norm": 2.6108484268188477,
+      "learning_rate": 0.00029922444889779557,
+      "loss": 13.10027618408203,
+      "step": 230
+    },
+    {
+      "epoch": 0.0048,
+      "grad_norm": 2.317113161087036,
+      "learning_rate": 0.00029916432865731456,
+      "loss": 10.390520477294922,
+      "step": 240
+    },
+    {
+      "epoch": 0.005,
+      "grad_norm": 2.3662290573120117,
+      "learning_rate": 0.00029910420841683367,
+      "loss": 11.516622924804688,
+      "step": 250
+    },
+    {
+      "epoch": 0.0052,
+      "grad_norm": 1.1160132884979248,
+      "learning_rate": 0.0002990440881763527,
+      "loss": 10.796371459960938,
+      "step": 260
+    },
+    {
+      "epoch": 0.0054,
+      "grad_norm": 2.113326072692871,
+      "learning_rate": 0.0002989839679358717,
+      "loss": 12.288037109375,
+      "step": 270
+    },
+    {
+      "epoch": 0.0056,
+      "grad_norm": 1.6802517175674438,
+      "learning_rate": 0.00029892384769539075,
+      "loss": 9.989302062988282,
+      "step": 280
+    },
+    {
+      "epoch": 0.0058,
+      "grad_norm": 0.667611300945282,
+      "learning_rate": 0.0002988637274549098,
+      "loss": 10.866537475585938,
+      "step": 290
+    },
+    {
+      "epoch": 0.006,
+      "grad_norm": 0.9238641858100891,
+      "learning_rate": 0.00029880360721442885,
+      "loss": 10.386916351318359,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -167,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3778874966016000.0,
+  "total_flos": 5668312449024000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null