Training in progress, step 280, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13f77a6e08b348f3bfb900b881b3c0efd47cddd13ccec836d46baf6594b6f3e2
+oid sha256:9ee790394f53b15b34064b0939918e9c8b9072447adc2a80ca76e194e588ef77
 size 2066752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f80b6d762e8051ccdd6210ef7b74a7ba43674bb3e1e3e7699e248b774548282e
+oid sha256:b600d0fdd76816945ac85cd28656988ce013a6ca21972288d9510ea639a3b024
 size 2162798

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5c9c2ffce3220f0a3b45e92be8237cbba5afc5034da73b9518a294a18be9087
+oid sha256:6573f71e16a24783361451616c22fd04c27282b0b2e2a2e59843f152dcef4214
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f2f956373db75de51d3c7ddd6d4c86d4b3f8ed55480d2a899fce0776e14a980
+oid sha256:ecf0e28c99191538a3c32f9899d55726f4960b122972e130d2555f6280416517
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3a36d0f4565e0cd31cd0465a8062a29bd158a6ba54be5d6acec2d94425b0892
+oid sha256:aa6ea3f731b59c0eb2ad9a4603b6f27b0a7e78ff027cc2874370bdf6bfc7598e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 20.0,
+  "epoch": 21.53846153846154,
   "eval_steps": 40,
-  "global_step": 260,
+  "global_step": 280,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -245,6 +245,28 @@
       "learning_rate": 0.00012985148110016947,
       "loss": 9.3153,
       "step": 260
+    },
+    {
+      "epoch": 20.76923076923077,
+      "grad_norm": 0.40234375,
+      "learning_rate": 0.00012454854871407994,
+      "loss": 9.2905,
+      "step": 270
+    },
+    {
+      "epoch": 21.53846153846154,
+      "grad_norm": 0.408203125,
+      "learning_rate": 0.00011917106319237386,
+      "loss": 9.2678,
+      "step": 280
+    },
+    {
+      "epoch": 21.53846153846154,
+      "eval_loss": 9.273423194885254,
+      "eval_runtime": 5.3547,
+      "eval_samples_per_second": 280.313,
+      "eval_steps_per_second": 4.482,
+      "step": 280
     }
   ],
   "logging_steps": 10,
@@ -264,7 +286,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 106381222871040.0,
+  "total_flos": 114564393861120.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null