Upload 8 files

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f4df0c785b7791245287fe1c5f680e6463fd9e47e7d8a4dbb5ea0c9105256ec
+oid sha256:417693109801c7441187e7add71a3bad8d2637305d3b4bd76ecd18306ef418b8
 size 18494040

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:445da9904e4385c935c446ab197148de99346155c2e6a4fe40680c2eab4c8124
+oid sha256:6037b31fbc3053fb0bad4fc42595272953fa60e94cfca460ea449291e2a5b05d
 size 37035002

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbdd2f29a31ef5687e75985709b03210edb0e25b1f2f17c9a08fb06f7dc22b57
+oid sha256:334b89593a1e587cb5ba4d78087b7def7081a35b3f61f6ea53a4250201c6477a
 size 1064

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.001,
+  "epoch": 0.0035,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 3500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -23,11 +23,51 @@
       "loss": 7.7872,
       "num_input_tokens_seen": 497906688,
       "step": 1000
+    },
+    {
+      "epoch": 0.0015,
+      "grad_norm": 0.43762627243995667,
+      "learning_rate": 5.6483913125652505e-05,
+      "loss": 7.0276,
+      "num_input_tokens_seen": 746696384,
+      "step": 1500
+    },
+    {
+      "epoch": 0.002,
+      "grad_norm": 0.47100603580474854,
+      "learning_rate": 5.645562874251497e-05,
+      "loss": 6.5612,
+      "num_input_tokens_seen": 994790144,
+      "step": 2000
+    },
+    {
+      "epoch": 0.0025,
+      "grad_norm": 0.4795113205909729,
+      "learning_rate": 5.642734435937744e-05,
+      "loss": 6.2086,
+      "num_input_tokens_seen": 1243917376,
+      "step": 2500
+    },
+    {
+      "epoch": 0.003,
+      "grad_norm": 0.9179026484489441,
+      "learning_rate": 5.63990599762399e-05,
+      "loss": 5.9393,
+      "num_input_tokens_seen": 1492823744,
+      "step": 3000
+    },
+    {
+      "epoch": 0.0035,
+      "grad_norm": 1.1793241500854492,
+      "learning_rate": 5.6370775593102374e-05,
+      "loss": 5.728,
+      "num_input_tokens_seen": 1742012864,
+      "step": 3500
     }
   ],
   "logging_steps": 500,
   "max_steps": 1000000,
-  "num_input_tokens_seen": 497906688,
+  "num_input_tokens_seen": 1742012864,
   "num_train_epochs": 9223372036854775807,
   "save_steps": 500,
   "stateful_callbacks": {
@@ -42,7 +82,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7687997923000320.0,
+  "total_flos": 2.689779350839296e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null