Training in progress, step 2600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa10074e1d6ddc94d23153c9734747c8baf91d47d6dba6666b1ef724ab871f8c
+oid sha256:0e0fe0e9d900d8fecd195e1a719802ba1ac5f49e274f580b73f4466c3f57dd5c
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9ab1eb9cd7c1ea28ecdf3adae9b1c04bcbc49f42a37845326b6ae05057c7199
+oid sha256:8ed18925aeed2c70e87f6e85275b0e2e7c1d48fcea3988e938200f4125c88c46
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66d8839ff66cb4b737720f4f9d1c90cc3202ad969b799aa3c2659a6ea5ff1a82
+oid sha256:a353eb9058a377bea13c7e9eeff43101bb2c4a8b11951234da6a710bb5053f86
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42f27a730b6ee07b80f832c5a86ad2126ba907f4b4cf4aa2e99d8c5986c6b885
+oid sha256:2e63d6cbad437bb2ff0881a0f3731290a112af9056e30047c433328ae16fc214
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9230769230769231,
+  "epoch": 0.9302325581395349,
   "eval_steps": 500,
-  "global_step": 2580,
+  "global_step": 2600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2071,14 +2071,30 @@
       "loss": 0.3949,
       "num_input_tokens_seen": 1748817,
       "step": 2580
+    },
+    {
+      "epoch": 0.9266547406082289,
+      "grad_norm": 0.31920483708381653,
+      "learning_rate": 1.4669051878354204e-05,
+      "loss": 0.3741,
+      "num_input_tokens_seen": 1754777,
+      "step": 2590
+    },
+    {
+      "epoch": 0.9302325581395349,
+      "grad_norm": 0.26824864745140076,
+      "learning_rate": 1.3953488372093024e-05,
+      "loss": 0.386,
+      "num_input_tokens_seen": 1762187,
+      "step": 2600
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1748817,
+  "num_input_tokens_seen": 1762187,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 3.932471857163674e+16,
+  "total_flos": 3.96253626569257e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null