Upload folder using huggingface_hub

checkpoint-latest/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca52a8b3016d203a936beddbcf117be824418aa83105a5b7c66cb6ee5e03d904
+oid sha256:987cdddaddd6ee9efcbf0406b5dbea003e19c76523f179ea3826ca2f5707f3cd
 size 62293080

checkpoint-latest/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3caa7486f45749552621cbfc1449a5f803a04e5ca4e0bb6a48abed87b6ae7f9c
+oid sha256:b4ea40a6da395d8e9289cbe3e64187c17945564d3b3cb832aeaf878ad5504ff8
 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/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": 107.876,
       "eval_steps_per_second": 4.151,
       "step": 2000
+    },
+    {
+      "epoch": 0.3739222241773711,
+      "grad_norm": 0.6693059802055359,
+      "learning_rate": 0.00026262537392222413,
+      "loss": 3.3749,
+      "step": 2125
+    },
+    {
+      "epoch": 0.3959176491289812,
+      "grad_norm": 0.8750757575035095,
+      "learning_rate": 0.00026042583142706316,
+      "loss": 3.3698,
+      "step": 2250
+    },
+    {
+      "epoch": 0.41791307408059125,
+      "grad_norm": 0.8450427651405334,
+      "learning_rate": 0.00025822628893190213,
+      "loss": 3.3556,
+      "step": 2375
+    },
+    {
+      "epoch": 0.4399084990322013,
+      "grad_norm": 0.660953938961029,
+      "learning_rate": 0.00025602674643674116,
+      "loss": 3.3503,
+      "step": 2500
+    },
+    {
+      "epoch": 0.4399084990322013,
+      "eval_loss": 2.8230228424072266,
+      "eval_runtime": 91.2675,
+      "eval_samples_per_second": 107.924,
+      "eval_steps_per_second": 4.153,
+      "step": 2500
+    },
+    {
+      "epoch": 0.46190392398381136,
+      "grad_norm": 0.7277446389198303,
+      "learning_rate": 0.00025382720394158013,
+      "loss": 3.358,
+      "step": 2625
+    },
+    {
+      "epoch": 0.4838993489354214,
+      "grad_norm": 0.7908076047897339,
+      "learning_rate": 0.0002516276614464191,
+      "loss": 3.3433,
+      "step": 2750
+    },
+    {
+      "epoch": 0.5058947738870315,
+      "grad_norm": 0.847932755947113,
+      "learning_rate": 0.00024942811895125813,
+      "loss": 3.3363,
+      "step": 2875
+    },
+    {
+      "epoch": 0.5278901988386415,
+      "grad_norm": 0.7486276626586914,
+      "learning_rate": 0.0002472285764560971,
+      "loss": 3.3197,
+      "step": 3000
+    },
+    {
+      "epoch": 0.5278901988386415,
+      "eval_loss": 2.7938477993011475,
+      "eval_runtime": 91.2355,
+      "eval_samples_per_second": 107.962,
+      "eval_steps_per_second": 4.154,
+      "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