Training in progress, step 1000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0081a644ccb2a3c99ec49d81f1998579fe51e05e6618ab20cdb3ec3dd8f2360c
+oid sha256:a6648a41237a7a2278ffd750717f8841ba95250a368dd73cc651be06f16d32f5
 size 241984552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d98cbd9c36bdbb9a3412b440c081fe77452a87ab60c5b5ba599577d8dcd7787f
+oid sha256:7918592fe825a53ce56575c6d5aa31d320545cf98ef41215df02d4d0d4887d73
 size 121457978

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c36f24c7557f34f0952c652dc5d3521e4985ade9d2001df573f64161a127017
+oid sha256:fb9a23fa52b27eaa5fc22b4213d74495fec88896724f361e788bf3955ddbac40
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adef1d896394d3056d6479942966d4f98d20571c0546546ab49e1820f23794b3
+oid sha256:8e220a0d9a44c971538f4556a11503eb3a8b03f14341ea5528fade0233a5550d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.11407711613050422,
+  "epoch": 0.22815423226100845,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -14,6 +14,13 @@
       "learning_rate": 9.771845767738991e-05,
       "loss": 1.2982,
       "step": 500
+    },
+    {
+      "epoch": 0.22815423226100845,
+      "grad_norm": 2.1173226833343506,
+      "learning_rate": 9.543691535477983e-05,
+      "loss": 0.9848,
+      "step": 1000
     }
   ],
   "logging_steps": 500,
@@ -21,7 +28,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 812050808832000.0,
+  "total_flos": 1624101617664000.0,
   "train_batch_size": 12,
   "trial_name": null,
   "trial_params": null