Upload folder using huggingface_hub

checkpoint-latest/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fd29ac343b2e0582fb8a887937c055cdcc418a58a57805fd2e8f97c4a9b5902
+oid sha256:ca78270c1eb66602a5b2542766d42a3fc8e325de3b96fce543a19e8e8bef7ca7
 size 62293080

checkpoint-latest/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f959a9f93fe8c29de8bad80e922cd938a2f1ded943f2da2478b6fa5c4adfd70
+oid sha256:e8e440d79ef49bcf712a1d5de898513d16e87c6d8ce5161401d087749466aa41
 size 124642443

checkpoint-latest/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:019869f04ad9e65816198cf9bbc88e01065d43c5ae26d3c4dfa75569351f838e
+oid sha256:5484747db8664edead11a8224a290c2af74f43eba04cf19c64277c5316deb36e
 size 14645

checkpoint-latest/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a377768ec214c80211f84cf49de0b3a1987fbbc2efbe16a70dc0f558f050f0a7
+oid sha256:1017972ceaff444cd6ce76f4cbc6776ac15954ae5dab86e347a964413d5e9fd6
 size 1465

checkpoint-latest/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.055780397677283,
+  "epoch": 1.2317437972901637,
   "eval_steps": 500,
-  "global_step": 6000,
+  "global_step": 7000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -440,6 +440,78 @@
       "eval_samples_per_second": 108.993,
       "eval_steps_per_second": 4.194,
       "step": 6000
+    },
+    {
+      "epoch": 1.0777758226288932,
+      "grad_norm": 0.8108923435211182,
+      "learning_rate": 0.00019224001407707196,
+      "loss": 3.1627,
+      "step": 6125
+    },
+    {
+      "epoch": 1.0997712475805033,
+      "grad_norm": 0.8860889077186584,
+      "learning_rate": 0.00019004047158191096,
+      "loss": 3.1703,
+      "step": 6250
+    },
+    {
+      "epoch": 1.1217666725321134,
+      "grad_norm": 0.6584394574165344,
+      "learning_rate": 0.00018784092908674993,
+      "loss": 3.1704,
+      "step": 6375
+    },
+    {
+      "epoch": 1.1437620974837235,
+      "grad_norm": 0.7717780470848083,
+      "learning_rate": 0.00018564138659158893,
+      "loss": 3.1712,
+      "step": 6500
+    },
+    {
+      "epoch": 1.1437620974837235,
+      "eval_loss": 2.6807186603546143,
+      "eval_runtime": 90.3407,
+      "eval_samples_per_second": 109.032,
+      "eval_steps_per_second": 4.195,
+      "step": 6500
+    },
+    {
+      "epoch": 1.1657575224353334,
+      "grad_norm": 0.666558563709259,
+      "learning_rate": 0.00018344184409642793,
+      "loss": 3.1564,
+      "step": 6625
+    },
+    {
+      "epoch": 1.1877529473869435,
+      "grad_norm": 0.8080345392227173,
+      "learning_rate": 0.0001812423016012669,
+      "loss": 3.1725,
+      "step": 6750
+    },
+    {
+      "epoch": 1.2097483723385536,
+      "grad_norm": 0.7759010791778564,
+      "learning_rate": 0.0001790427591061059,
+      "loss": 3.1469,
+      "step": 6875
+    },
+    {
+      "epoch": 1.2317437972901637,
+      "grad_norm": 0.7258739471435547,
+      "learning_rate": 0.00017684321661094488,
+      "loss": 3.147,
+      "step": 7000
+    },
+    {
+      "epoch": 1.2317437972901637,
+      "eval_loss": 2.674105405807495,
+      "eval_runtime": 90.5221,
+      "eval_samples_per_second": 108.813,
+      "eval_steps_per_second": 4.187,
+      "step": 7000
     }
   ],
   "logging_steps": 125,
@@ -459,7 +531,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3520096723009536.0,
+  "total_flos": 4106809598017536.0,
   "train_batch_size": 26,
   "trial_name": null,
   "trial_params": null