Training in progress, step 80, checkpoint

last-checkpoint/model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca78c56901396f034547c9a389a8248cba7409ee84cf453dd7bfa8c03d2a7e43
+oid sha256:6a139fa3d38532608eff536a5d3dcf335ee9c3ee0d23035ea4a153911168cb42
 size 4972163696

last-checkpoint/model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:672f2a2870cbcbcc5ea6c5027d2e0fbce4de08c42b10c83315612fcda56617db
+oid sha256:0df432724d992eaad816422a0eb57fdc3091c5fdd65bf269c4ba5e9e93d3f6c5
 size 2669366920

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9db8761eb7ef6153de6524361d61df1be9569589d82343778180eb252038c1e
+oid sha256:272554cc2b6b78a403d76f2c82bb9f3a72612eff4ab11a91bb08e4f9afa0699b
 size 7762295162

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbbc0a86104f167e435d82d912099d9f4e8e28814d0b3054a66bc62faad66266
+oid sha256:f845cccc365f42082caa7da8e604f0c659004980fe3b3663dcc7e14c2ca04bce
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab9aca62c8968a97eee76d9db5ace24bd5602b66748ad8ebaa3c5beb481c0acd
+oid sha256:8dc2365c0dcf059a80feab8740ee48b0ab99d23a36a4fcdd0867be4b5ceb6e9e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ecef8be965f4a8a3ed32d79c73f9a4a9b6fc06e37821a549724a0a8e8322513
+oid sha256:9dfa48462bc67143df2cd639a35fe858a2249d5fc29a8dbef955d03c6c86c4f8
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0d44c275e240e610f81071dc60b4fd4a20c4c4c06cc32abe80112f3f1a29d61
+oid sha256:1b88a2d1f28d47a4c4e8ea38eec6b15121f358a10dad34451756b36840a679ec
 size 15024

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": 1.1320754716981132,
+  "epoch": 1.509433962264151,
   "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": 70.087,
       "eval_steps_per_second": 4.389,
       "step": 60
+    },
+    {
+      "epoch": 1.320754716981132,
+      "grad_norm": 0.85546875,
+      "learning_rate": 0.00019757963826274357,
+      "loss": 1.2583,
+      "step": 70
+    },
+    {
+      "epoch": 1.509433962264151,
+      "grad_norm": 0.90625,
+      "learning_rate": 0.00019622680003092503,
+      "loss": 1.0736,
+      "step": 80
+    },
+    {
+      "epoch": 1.509433962264151,
+      "eval_loss": 1.7416529655456543,
+      "eval_runtime": 32.0268,
+      "eval_samples_per_second": 46.867,
+      "eval_steps_per_second": 2.935,
+      "step": 80
     }
   ],
   "logging_steps": 10,
@@ -100,7 +122,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.386566654079795e+16,
+  "total_flos": 5.850280234267443e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null