Training in progress, step 2000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9b57975ef2553ddb45b17e8639e5c792ae6a9db241080f3921772a663b5cdd9
+oid sha256:92a0e91accf4228b98caf6fb1d285323d5a1184a6a49e46d0af865a8d6eb057c
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:264d4479fdd4c1c3edd354dafde669db80fb296f7780bfcfde719c431def59f8
+oid sha256:1ba08a854f6c958770b50e1d0470ae9e0d583109948b4cdfe1d08bd223264cfd
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20294402676b8b8232d3be0cb80a9ffb92a161c28d7847bfbca2a9db648b436d
+oid sha256:4e0045739043a1f47643b813cbabc473141dd79658dbb66a9080e37f01080f2a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42b1986334441b860a3077d8e5be92854d188d88bc5cb1fd4f52e91ff8996e40
+oid sha256:9866a2fe0d11157ea657698adf310adebc8af3b7e4ad7c6e0bfe9124b0e7f879
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1,
+  "epoch": 0.13333333333333333,
   "eval_steps": 500,
-  "global_step": 1500,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -112,6 +112,41 @@
       "learning_rate": 1.9334222222222223e-05,
       "loss": 0.0761,
       "step": 1500
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 0.12180228531360626,
+      "learning_rate": 1.928977777777778e-05,
+      "loss": 0.0777,
+      "step": 1600
+    },
+    {
+      "epoch": 0.11333333333333333,
+      "grad_norm": 0.3697006106376648,
+      "learning_rate": 1.9245333333333337e-05,
+      "loss": 0.0828,
+      "step": 1700
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.08333831280469894,
+      "learning_rate": 1.9200888888888892e-05,
+      "loss": 0.0755,
+      "step": 1800
+    },
+    {
+      "epoch": 0.12666666666666668,
+      "grad_norm": 0.191595196723938,
+      "learning_rate": 1.9156444444444447e-05,
+      "loss": 0.0788,
+      "step": 1900
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.13422241806983948,
+      "learning_rate": 1.9112000000000003e-05,
+      "loss": 0.0756,
+      "step": 2000
     }
   ],
   "logging_steps": 100,
@@ -131,7 +166,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3653747343360000.0,
+  "total_flos": 4871663124480000.0,
   "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