Training in progress, step 1500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91ffd4788c4ea759629dc808cb051ca7eab384e5fb8ae9dfa2d14c415beef6ab
+oid sha256:d9b57975ef2553ddb45b17e8639e5c792ae6a9db241080f3921772a663b5cdd9
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:282c89d11dc548c714ac38e7fb510faacb72a5ed4d68eccfbd51cd63307f0bdc
+oid sha256:264d4479fdd4c1c3edd354dafde669db80fb296f7780bfcfde719c431def59f8
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a7bccffbe4567a72e1b938cd6f7b1d19b05b0d573111e28fd70761fd6902354
+oid sha256:20294402676b8b8232d3be0cb80a9ffb92a161c28d7847bfbca2a9db648b436d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86c73fa767afb78abc2698cb0a4494c23586bafd962eae88fa8af29f90657dc4
+oid sha256:42b1986334441b860a3077d8e5be92854d188d88bc5cb1fd4f52e91ff8996e40
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06666666666666667,
+  "epoch": 0.1,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -77,6 +77,41 @@
       "learning_rate": 1.9556444444444447e-05,
       "loss": 0.0851,
       "step": 1000
+    },
+    {
+      "epoch": 0.07333333333333333,
+      "grad_norm": 0.3818432092666626,
+      "learning_rate": 1.9512000000000002e-05,
+      "loss": 0.0816,
+      "step": 1100
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.24892888963222504,
+      "learning_rate": 1.9467555555555557e-05,
+      "loss": 0.0812,
+      "step": 1200
+    },
+    {
+      "epoch": 0.08666666666666667,
+      "grad_norm": 0.2256750911474228,
+      "learning_rate": 1.9423111111111113e-05,
+      "loss": 0.0772,
+      "step": 1300
+    },
+    {
+      "epoch": 0.09333333333333334,
+      "grad_norm": 0.1860508769750595,
+      "learning_rate": 1.9378666666666668e-05,
+      "loss": 0.0781,
+      "step": 1400
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.3207520544528961,
+      "learning_rate": 1.9334222222222223e-05,
+      "loss": 0.0761,
+      "step": 1500
     }
   ],
   "logging_steps": 100,
@@ -96,7 +131,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2435831562240000.0,
+  "total_flos": 3653747343360000.0,
   "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