Training in progress, step 1500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c391de231f7ed92186d1a10241a7ab5e952075a13c23d6b84b45492cee3429f0
+oid sha256:8a023c9a555a15156bd1f3b0eac50642921f8896cc49d86705ca5e46e1a3dea4
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faad0a21dc9b580a03e494fae6387e0a3b73c49e378acf3d445af2e73b59951b
+oid sha256:20cb133af12395f0079a6433185baec87512b5142bbe45d5c7ead264b147a62b
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ca61b35c59ebd89a4825d5fbf02c06acba38873c8cf9ce9e1e69e27d21b4b17
+oid sha256:6770c13dffdadbdc7c80304e0bdb979e4d2486cbabf9dbf5458aa9c0e4bdb14e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed33a752681152f4a94d0c64e56b596a28750fb35fe8a480a0094b3610dd201e
+oid sha256:8319a7acfebd28a7d1b9834780aa2fdd6ff752ee848c5da2e67c4cf03efbd1a9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5295169946332737,
+  "epoch": 0.5366726296958855,
   "eval_steps": 500,
-  "global_step": 1480,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1191,14 +1191,30 @@
       "loss": 0.4019,
       "num_input_tokens_seen": 995054,
       "step": 1480
+    },
+    {
+      "epoch": 0.5330948121645797,
+      "grad_norm": 0.3645225465297699,
+      "learning_rate": 9.338103756708408e-05,
+      "loss": 0.4038,
+      "num_input_tokens_seen": 1001348,
+      "step": 1490
+    },
+    {
+      "epoch": 0.5366726296958855,
+      "grad_norm": 0.25708308815956116,
+      "learning_rate": 9.26654740608229e-05,
+      "loss": 0.4016,
+      "num_input_tokens_seen": 1007269,
+      "step": 1500
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 995054,
+  "num_input_tokens_seen": 1007269,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 2.237525053426483e+16,
+  "total_flos": 2.264992274831155e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null