Training in progress, step 80, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c1610b7eff6437eb2bb63e5dfdf8b49331eb71e4617388f7ffda9dbed527b51
+oid sha256:7a845c37c43ad9337b2921423d609a972ceaae5b1912f8ef370db95fce81ed3e
 size 250490408

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6e4c79a7e172ff7a4a912a2b1375c8d27c5c42763d3fae57a462b66c71b68d2
+oid sha256:f2a69423bd2f85a3cb77effdb9583e4539e6b3e63bc98bd5f6bec4e02bc44df4
 size 255265850

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:143f5b4f9034575ed8875b5384514453e6af653a08c123c1e944efd394f8efc4
+oid sha256:22171af70cffee5f380e1336353e06904e40202cafcf0b44991e820c034f9a1d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b88ba6c6448836e3a8e625dcc4fe1c126d0b8f1a9400e26128b640c6a1a4e25e
+oid sha256:814445e8c97a1d090f0500a145fa38cc3b150850d76a622c09dc8d7720d6070b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cb84bcc6e01403e7801ab46f03b72f577573daa0707f696fa7bd5ccf50adf21
+oid sha256:2ceb997af1461f413df7026c0297eec218ef5efb08cee2d5237d66f270eb535e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b6871625d54b2a1c5dbdd4ab6f1b61571d8205213dfb7c2b7cfd35f43eefcc4
+oid sha256:2d88b7788659022a87572b128e431cdef971fa16742897741033f21525c1d5c8
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f299ab56b5f200cab03608b3ac75cf1761ca29c2207c1dfe5ab919b66f8dbd88
+oid sha256:c420644371984c0c279fff13e73e1c3067315dc564ce90ee02e2ca237d8a9e35
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.0,
+  "epoch": 13.333333333333334,
   "eval_steps": 20,
-  "global_step": 60,
+  "global_step": 80,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -81,6 +81,28 @@
       "eval_samples_per_second": 289.528,
       "eval_steps_per_second": 2.315,
       "step": 60
+    },
+    {
+      "epoch": 11.666666666666666,
+      "grad_norm": 2.171875,
+      "learning_rate": 4.530518418775733e-05,
+      "loss": 4.5465,
+      "step": 70
+    },
+    {
+      "epoch": 13.333333333333334,
+      "grad_norm": 2.34375,
+      "learning_rate": 2.1085949060360654e-05,
+      "loss": 4.484,
+      "step": 80
+    },
+    {
+      "epoch": 13.333333333333334,
+      "eval_loss": 3.219902276992798,
+      "eval_runtime": 5.4176,
+      "eval_samples_per_second": 277.061,
+      "eval_steps_per_second": 2.215,
+      "step": 80
     }
   ],
   "logging_steps": 10,
@@ -100,7 +122,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7772915579748352.0,
+  "total_flos": 1.0372248846204928e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null