Training in progress, step 80, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e77001dd01949849df6db7c281e4f173c2772a5c29a9acfcc0a291204cac94d7
+oid sha256:ac3c5cb2e77aa09de86102669fab0a58c5fbb2fac38941de01eaa06680ecd6b5
 size 2066752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7121aaf20e1078f0517c2a16980937c88f6dfbb0b414dd833b71f937a7e4b67
+oid sha256:7de1afa08e042afe2b7724794e5abc6b3c2844ee734ce29154ef19d4db24a536
 size 2162798

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cb4d60225d8c48e38a702d9643499b1191b9397c9d0952b41200b5d100ae38b
+oid sha256:e4789394f5e9bf3695e87ba89acf1261237e8f92d8ca463a31a9d39185674969
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2aec0ba2a5c752d849e13597ae7bab4da49c31f7c4cd960e7c1948813502041f
+oid sha256:95830d8f799e5857092ffa30bec2dad56d615ec4ba20eae91e7157878213510f
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3671bd7fce476af6c5d68b2346a8d63f3c9e317781066d2c00973b04663cf26
+oid sha256:5258a10d326b43bb322f9f7412c08a5d462c4dd53d2018b15d95caea3824d34f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.615384615384615,
+  "epoch": 6.153846153846154,
   "eval_steps": 40,
-  "global_step": 60,
+  "global_step": 80,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -65,6 +65,28 @@
       "learning_rate": 0.00019863613034027224,
       "loss": 10.2518,
       "step": 60
+    },
+    {
+      "epoch": 5.384615384615385,
+      "grad_norm": 0.326171875,
+      "learning_rate": 0.00019757963826274357,
+      "loss": 10.1828,
+      "step": 70
+    },
+    {
+      "epoch": 6.153846153846154,
+      "grad_norm": 0.330078125,
+      "learning_rate": 0.00019622680003092503,
+      "loss": 10.1177,
+      "step": 80
+    },
+    {
+      "epoch": 6.153846153846154,
+      "eval_loss": 10.088459014892578,
+      "eval_runtime": 5.2612,
+      "eval_samples_per_second": 285.294,
+      "eval_steps_per_second": 4.562,
+      "step": 80
     }
   ],
   "logging_steps": 10,
@@ -84,7 +106,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 24549512970240.0,
+  "total_flos": 32732683960320.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null