Training in progress, step 2280, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5077a398af295249ce2f4d98872ffaaf66d62ab91667ded3732057696cb98d05
+oid sha256:b4d0e6f6e105ca8708dd58c58cac0d38ef3d7e182e4118c1d7c3bbbb4cfbb8e5
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f37afe2c737cc2e3e0daf8579556cc1d76cf5d3b7d751612fad5ffa14825dfc
+oid sha256:5fe2060f54f8854e34b115c7210a27ece708af54ff47a9aed67412ee4f2d4639
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:200623e06ecf672802d7eae0c71722793b083804f6358d7108007423c07e494e
+oid sha256:1817c09855fd07da9d0e441c81f4b0b9ce05c1e1787ca7dcb5d996cd39c530fd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f24aa350ef290461846581cc1e60d9a5fe6b837e2dd0a4ee4c53e1368aeb953
+oid sha256:36cd02824fbe35ffd9c39b1765aeeef980a727adc03234507c83ce617d1b746f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8085867620751341,
+  "epoch": 0.815742397137746,
   "eval_steps": 500,
-  "global_step": 2260,
+  "global_step": 2280,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1815,14 +1815,30 @@
       "loss": 0.369,
       "num_input_tokens_seen": 1530483,
       "step": 2260
+    },
+    {
+      "epoch": 0.8121645796064401,
+      "grad_norm": 0.31918245553970337,
+      "learning_rate": 3.756708407871199e-05,
+      "loss": 0.4161,
+      "num_input_tokens_seen": 1538556,
+      "step": 2270
+    },
+    {
+      "epoch": 0.815742397137746,
+      "grad_norm": 0.36853113770484924,
+      "learning_rate": 3.685152057245081e-05,
+      "loss": 0.3834,
+      "num_input_tokens_seen": 1545040,
+      "step": 2280
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1530483,
+  "num_input_tokens_seen": 1545040,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 3.4415157934577664e+16,
+  "total_flos": 3.474249345810432e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null