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 sha256:2392bcb18cf6a8e1a05a1d93ca356ffd43cfb5139c9f132e4c34270f8b6835cc
+oid sha256:75c9311f17b632d216095e4d5931d56cdc53c3d92ceddbd43f832361e3ba80e7
 size 4995335576

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59f3a5c06cfe114b367ef79249b8fa1a476f4089babf7356b1705e36960af7f7
+oid sha256:a811774024d37ebfd9d0599b034618ce7f1ae85b999eafcf1e61c3f77ff84ae9
 size 1857639032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d02dd6f18eb9beef1ba890d470e04ef8069a1d28c8636c6640b6e9693e3ac119
+oid sha256:a33399416f26c080a1123dec2edfb2bdc08a4a6fca6afe747e35009ede5e0f35
 size 6961290854

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": 1.5,
+  "epoch": 2.0,
   "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": 105.877,
       "eval_steps_per_second": 5.361,
       "step": 60
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.984375,
+      "learning_rate": 0.00019757963826274357,
+      "loss": 1.0686,
+      "step": 70
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.1484375,
+      "learning_rate": 0.00019622680003092503,
+      "loss": 1.1259,
+      "step": 80
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.0676190853118896,
+      "eval_runtime": 14.1344,
+      "eval_samples_per_second": 106.194,
+      "eval_steps_per_second": 5.377,
+      "step": 80
     }
   ],
   "logging_steps": 10,
@@ -100,7 +122,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.889291985518592e+16,
+  "total_flos": 6.514971359418778e+16,
   "train_batch_size": 5,
   "trial_name": null,
   "trial_params": null