Training in progress, step 1180, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b0dd6d9eecd111fc6fbe2ea756eb3599bab074e1522852ef4565a8d0ad6a8c8
+oid sha256:cf7ba55347be3009d65b0f6e45243c095cb0115dd9730e83831a737d420ed7d8
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:311a37a787f8e244031ec691411ba1c79ba76c28a8310c7bb68b2848e9a6c30e
+oid sha256:8ce7a1b50c1cfa308c27e5cb3651542491d426a9f882fb92cb544cabeb70bb31
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:347b707ba8c2977c0e73867f80277a74052c00e5d1c0dbac8e14d68e38fd054c
+oid sha256:ecb8413f834d7aea22eaaf4929929d97571a7bcc98ba8e7df76bc3dfd61eff41
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e645a96d4cb253e4a9c4e19eba1a73b1611a46e51a63b85e8070050f71348c7
+oid sha256:db27570aff99c68af4609f5f7c05632809723cb9d1da7a19356fc2b24a3fe3ec
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4150268336314848,
+  "epoch": 0.4221824686940966,
   "eval_steps": 500,
-  "global_step": 1160,
+  "global_step": 1180,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -935,14 +935,30 @@
       "loss": 0.3937,
       "num_input_tokens_seen": 778619,
       "step": 1160
+    },
+    {
+      "epoch": 0.4186046511627907,
+      "grad_norm": 0.24456287920475006,
+      "learning_rate": 0.00011627906976744187,
+      "loss": 0.4264,
+      "num_input_tokens_seen": 787085,
+      "step": 1170
+    },
+    {
+      "epoch": 0.4221824686940966,
+      "grad_norm": 0.2968457341194153,
+      "learning_rate": 0.00011556350626118069,
+      "loss": 0.4196,
+      "num_input_tokens_seen": 794103,
+      "step": 1180
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 778619,
+  "num_input_tokens_seen": 794103,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 1.7508391701092352e+16,
+  "total_flos": 1.7856572181018624e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null