Upload folder using huggingface_hub

checkpoint-latest/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef513511cab07aae2229c81db3abdc654a0b3295a3c2d11cbd3d6499af06ee82
+oid sha256:6f75126c2a34822f1bd2758385a8fd1ca1669f4dff9de1317e4f5b25887d0a0d
 size 62293080

checkpoint-latest/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28fc9a9bbe9b73a2b142749dd94f1bfc0455d15809207712e61bb52c170e192c
+oid sha256:1b94ba484a1c3a45fc8e9c69eeda0cff023c2452e3377a4ee8a9ae36f58df97f
 size 124642443

checkpoint-latest/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9ab924d1dd6f7d0d0a987395af92fe2c207d68f4ed0046e34205bf59aa0a3e7
+oid sha256:2b7133fcea647449b2caaa65223ebbc0c180189bbd59dbe842634047836d81e2
 size 14645

checkpoint-latest/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09920373f9c73ff341f9b497a1508313129ce162304c3799289a6c23932f7385
+oid sha256:e26664050c6d90fb565d76db26661576aa404ce53418da0b68344264e2ee7e47
 size 1383

checkpoint-latest/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:733b6a45fd8cebd94fb50b1fb141fd687689caaa2ac76b306c6159a539b547e5
+oid sha256:ac8a8c1f0ca136b116df977b16704d013fad49cab357d7231675ec3945e85ad2
 size 1465

checkpoint-latest/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.35192679922576103,
+  "epoch": 0.5278901988386415,
   "eval_steps": 500,
-  "global_step": 2000,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -152,6 +152,78 @@
       "eval_samples_per_second": 167.039,
       "eval_steps_per_second": 6.427,
       "step": 2000
+    },
+    {
+      "epoch": 0.3739222241773711,
+      "grad_norm": 0.7473997473716736,
+      "learning_rate": 0.00026262537392222413,
+      "loss": 3.072,
+      "step": 2125
+    },
+    {
+      "epoch": 0.3959176491289812,
+      "grad_norm": 0.8357605338096619,
+      "learning_rate": 0.00026042583142706316,
+      "loss": 3.073,
+      "step": 2250
+    },
+    {
+      "epoch": 0.41791307408059125,
+      "grad_norm": 0.6772239804267883,
+      "learning_rate": 0.00025822628893190213,
+      "loss": 3.0631,
+      "step": 2375
+    },
+    {
+      "epoch": 0.4399084990322013,
+      "grad_norm": 0.8163031339645386,
+      "learning_rate": 0.00025602674643674116,
+      "loss": 3.0659,
+      "step": 2500
+    },
+    {
+      "epoch": 0.4399084990322013,
+      "eval_loss": 2.623256206512451,
+      "eval_runtime": 59.1416,
+      "eval_samples_per_second": 166.55,
+      "eval_steps_per_second": 6.408,
+      "step": 2500
+    },
+    {
+      "epoch": 0.46190392398381136,
+      "grad_norm": 0.7648818492889404,
+      "learning_rate": 0.00025382720394158013,
+      "loss": 3.0765,
+      "step": 2625
+    },
+    {
+      "epoch": 0.4838993489354214,
+      "grad_norm": 0.8686987161636353,
+      "learning_rate": 0.0002516276614464191,
+      "loss": 3.075,
+      "step": 2750
+    },
+    {
+      "epoch": 0.5058947738870315,
+      "grad_norm": 0.721097469329834,
+      "learning_rate": 0.00024942811895125813,
+      "loss": 3.1497,
+      "step": 2875
+    },
+    {
+      "epoch": 0.5278901988386415,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0002472285764560971,
+      "loss": 3.9227,
+      "step": 3000
+    },
+    {
+      "epoch": 0.5278901988386415,
+      "eval_loss": 3.1224141120910645,
+      "eval_runtime": 59.1848,
+      "eval_samples_per_second": 166.428,
+      "eval_steps_per_second": 6.404,
+      "step": 3000
     }
   ],
   "logging_steps": 125,
@@ -171,7 +243,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1173425750016000.0,
+  "total_flos": 1760138625024000.0,
   "train_batch_size": 26,
   "trial_name": null,
   "trial_params": null