Training in progress, step 2300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4d0e6f6e105ca8708dd58c58cac0d38ef3d7e182e4118c1d7c3bbbb4cfbb8e5
+oid sha256:f78f8e128e75e11b3bd24fe3cafa27eb00c4b149658842b4a45b224ec5f5ee22
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fe2060f54f8854e34b115c7210a27ece708af54ff47a9aed67412ee4f2d4639
+oid sha256:b815a874278b1223221c3e50dc80f1ff0a4372ec10c87401ec27f3ea0c36a67a
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1817c09855fd07da9d0e441c81f4b0b9ce05c1e1787ca7dcb5d996cd39c530fd
+oid sha256:502b3acd424d63dc379a6747cfdc8fa58c6c30b6487e9ba722dee624541749e4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36cd02824fbe35ffd9c39b1765aeeef980a727adc03234507c83ce617d1b746f
+oid sha256:fc458452416b9e8ad2bf3686e504ce90d7aec8e9da53788a9e1ab68961ab5745
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.815742397137746,
+  "epoch": 0.8228980322003577,
   "eval_steps": 500,
-  "global_step": 2280,
+  "global_step": 2300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1831,14 +1831,30 @@
       "loss": 0.3834,
       "num_input_tokens_seen": 1545040,
       "step": 2280
+    },
+    {
+      "epoch": 0.8193202146690519,
+      "grad_norm": 0.5155879855155945,
+      "learning_rate": 3.6135957066189624e-05,
+      "loss": 0.3814,
+      "num_input_tokens_seen": 1552028,
+      "step": 2290
+    },
+    {
+      "epoch": 0.8228980322003577,
+      "grad_norm": 0.2956937551498413,
+      "learning_rate": 3.5420393559928444e-05,
+      "loss": 0.395,
+      "num_input_tokens_seen": 1559137,
+      "step": 2300
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1545040,
+  "num_input_tokens_seen": 1559137,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 3.474249345810432e+16,
+  "total_flos": 3.5059485206071296e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null