Training in progress, step 1200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf7ba55347be3009d65b0f6e45243c095cb0115dd9730e83831a737d420ed7d8
+oid sha256:a978d2ea4c2ef178cab56e079e834d41ad51771ce490d4892a323b4ec39be6be
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ce7a1b50c1cfa308c27e5cb3651542491d426a9f882fb92cb544cabeb70bb31
+oid sha256:469403812ebd6b0168f1cfd10dc9051127cd1573ac3bdf23aca7e0e5a8a0418b
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecb8413f834d7aea22eaaf4929929d97571a7bcc98ba8e7df76bc3dfd61eff41
+oid sha256:6c4a6bdcee541f4bc227f467016d9bc346f4f8483027f6990cb0f3a9b7a1f71e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db27570aff99c68af4609f5f7c05632809723cb9d1da7a19356fc2b24a3fe3ec
+oid sha256:d836f79887d280f068e10ec79168f2ea91f57c6fbb35eab33b10757b0316f93b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4221824686940966,
+  "epoch": 0.4293381037567084,
   "eval_steps": 500,
-  "global_step": 1180,
+  "global_step": 1200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -951,14 +951,30 @@
       "loss": 0.4196,
       "num_input_tokens_seen": 794103,
       "step": 1180
+    },
+    {
+      "epoch": 0.4257602862254025,
+      "grad_norm": 0.3390592038631439,
+      "learning_rate": 0.00011484794275491951,
+      "loss": 0.4073,
+      "num_input_tokens_seen": 800033,
+      "step": 1190
+    },
+    {
+      "epoch": 0.4293381037567084,
+      "grad_norm": 0.35398080945014954,
+      "learning_rate": 0.00011413237924865831,
+      "loss": 0.4032,
+      "num_input_tokens_seen": 807607,
+      "step": 1200
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 794103,
+  "num_input_tokens_seen": 807607,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 1.7856572181018624e+16,
+  "total_flos": 1.8160229453101056e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null