Training in progress, step 1380, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4c36ddd34e5f64d6b8d72f7535780e3421a848c056451338ad60b3bc23355ca
+oid sha256:6b616fe2eb021d20d4875636738be3ca7342fc6db866fd391eb53743dd565cb0
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8441702a5d48998055bebf8bf17f52c9868b1176bcfd106766c5daef35e2005
+oid sha256:5356f6af8453685dfcd2ab29084ffd177cb62b8eaee4a3289a76f99910495ddc
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a125d9b0ccf3b1e15af9c78c7573f334a287768d58700d4bae393ced8e6486ba
+oid sha256:44f04742b905a4ba4f17b43b2fddc49db3e772b856badc745872559eec73cca5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9822ffd7b1cdab49a87c2ee8fe2f970274c45f8492d363a6e7b14647c57922bd
+oid sha256:bc40c38146bda7179f03752fd8672ec7d4feef1519e7b61e194eda1f35f35156
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4865831842576029,
+  "epoch": 0.4937388193202147,
   "eval_steps": 500,
-  "global_step": 1360,
+  "global_step": 1380,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1095,14 +1095,30 @@
       "loss": 0.4049,
       "num_input_tokens_seen": 915272,
       "step": 1360
+    },
+    {
+      "epoch": 0.49016100178890876,
+      "grad_norm": 0.249292254447937,
+      "learning_rate": 0.00010196779964221825,
+      "loss": 0.4064,
+      "num_input_tokens_seen": 921729,
+      "step": 1370
+    },
+    {
+      "epoch": 0.4937388193202147,
+      "grad_norm": 0.2855275869369507,
+      "learning_rate": 0.00010125223613595707,
+      "loss": 0.4092,
+      "num_input_tokens_seen": 928645,
+      "step": 1380
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 915272,
+  "num_input_tokens_seen": 928645,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 2.0581235095781376e+16,
+  "total_flos": 2.088194664047616e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null