Training in progress, step 1000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3331e477755949427e95b7dca968d6817d55bd6f917b4a8c3697b379a8dc4de9
+oid sha256:91ffd4788c4ea759629dc808cb051ca7eab384e5fb8ae9dfa2d14c415beef6ab
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d149c0078e7e5d6a67271171e08cca30c493c0a67019446d7d12b6b87d869ef3
+oid sha256:282c89d11dc548c714ac38e7fb510faacb72a5ed4d68eccfbd51cd63307f0bdc
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eeb00119856714d9031cbc8ce0f99dda5a9e485f405270a39f2ed5786c90b1b6
+oid sha256:8a7bccffbe4567a72e1b938cd6f7b1d19b05b0d573111e28fd70761fd6902354
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e8e1fdd83e33f36b55c6b8b26ed0abf72653733f5da9946c6d0ff99fd8c1f8d
+oid sha256:86c73fa767afb78abc2698cb0a4494c23586bafd962eae88fa8af29f90657dc4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03333333333333333,
+  "epoch": 0.06666666666666667,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -42,6 +42,41 @@
       "learning_rate": 1.9778666666666667e-05,
       "loss": 0.0887,
       "step": 500
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.30884480476379395,
+      "learning_rate": 1.9734222222222223e-05,
+      "loss": 0.0926,
+      "step": 600
+    },
+    {
+      "epoch": 0.04666666666666667,
+      "grad_norm": 0.14888174831867218,
+      "learning_rate": 1.9689777777777778e-05,
+      "loss": 0.0859,
+      "step": 700
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 0.23004640638828278,
+      "learning_rate": 1.9645333333333333e-05,
+      "loss": 0.0851,
+      "step": 800
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.38090068101882935,
+      "learning_rate": 1.9600888888888892e-05,
+      "loss": 0.0824,
+      "step": 900
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 0.12699204683303833,
+      "learning_rate": 1.9556444444444447e-05,
+      "loss": 0.0851,
+      "step": 1000
     }
   ],
   "logging_steps": 100,
@@ -61,7 +96,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1217915781120000.0,
+  "total_flos": 2435831562240000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5da3872b72c31dc28c756543e89c64090a6cb637a3a5de22e6dfe587939acf42
+oid sha256:20d7bfd722c356d3138649856f039df4c593cfd472f7e9aa290a4571f1e6327f
 size 5432