Upload folder using huggingface_hub

checkpoint-latest/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4a72b777dacb3233b793d6f7ff120365156aae60f5dbba910787412b7cacf38
+oid sha256:ca52a8b3016d203a936beddbcf117be824418aa83105a5b7c66cb6ee5e03d904
 size 62293080

checkpoint-latest/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d340f82181a0b7aa517f825860842f4e7c4f8a488329d59aadf3546361d8cd0
+oid sha256:3caa7486f45749552621cbfc1449a5f803a04e5ca4e0bb6a48abed87b6ae7f9c
 size 124642443

checkpoint-latest/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b182b3dedf0ef16e42c7c650dc1dabae1c16baddbc2124f22d1cc0600b2e9222
+oid sha256:b9ab924d1dd6f7d0d0a987395af92fe2c207d68f4ed0046e34205bf59aa0a3e7
 size 14645

checkpoint-latest/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6a5728e17488e0af5b9594b7a742e2aa414b404c43f45b9b8c470ef12744e2b
+oid sha256:733b6a45fd8cebd94fb50b1fb141fd687689caaa2ac76b306c6159a539b547e5
 size 1465

checkpoint-latest/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.17596339961288052,
+  "epoch": 0.35192679922576103,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -80,6 +80,78 @@
       "eval_samples_per_second": 114.915,
       "eval_steps_per_second": 4.422,
       "step": 1000
+    },
+    {
+      "epoch": 0.1979588245644906,
+      "grad_norm": 0.8066490292549133,
+      "learning_rate": 0.0002802217138835122,
+      "loss": 3.5005,
+      "step": 1125
+    },
+    {
+      "epoch": 0.21995424951610065,
+      "grad_norm": 0.7767718434333801,
+      "learning_rate": 0.0002780221713883512,
+      "loss": 3.4749,
+      "step": 1250
+    },
+    {
+      "epoch": 0.2419496744677107,
+      "grad_norm": 0.7831096053123474,
+      "learning_rate": 0.0002758226288931902,
+      "loss": 3.4609,
+      "step": 1375
+    },
+    {
+      "epoch": 0.26394509941932076,
+      "grad_norm": 0.9593456387519836,
+      "learning_rate": 0.0002736230863980292,
+      "loss": 3.4383,
+      "step": 1500
+    },
+    {
+      "epoch": 0.26394509941932076,
+      "eval_loss": 2.885742664337158,
+      "eval_runtime": 91.283,
+      "eval_samples_per_second": 107.906,
+      "eval_steps_per_second": 4.152,
+      "step": 1500
+    },
+    {
+      "epoch": 0.28594052437093087,
+      "grad_norm": 0.7641668915748596,
+      "learning_rate": 0.0002714235439028682,
+      "loss": 3.4404,
+      "step": 1625
+    },
+    {
+      "epoch": 0.3079359493225409,
+      "grad_norm": 0.71437668800354,
+      "learning_rate": 0.00026922400140770716,
+      "loss": 3.4147,
+      "step": 1750
+    },
+    {
+      "epoch": 0.329931374274151,
+      "grad_norm": 0.7094811201095581,
+      "learning_rate": 0.0002670244589125462,
+      "loss": 3.4125,
+      "step": 1875
+    },
+    {
+      "epoch": 0.35192679922576103,
+      "grad_norm": 0.722710907459259,
+      "learning_rate": 0.00026482491641738516,
+      "loss": 3.3959,
+      "step": 2000
+    },
+    {
+      "epoch": 0.35192679922576103,
+      "eval_loss": 2.8463189601898193,
+      "eval_runtime": 91.3088,
+      "eval_samples_per_second": 107.876,
+      "eval_steps_per_second": 4.151,
+      "step": 2000
     }
   ],
   "logging_steps": 125,
@@ -99,7 +171,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 586712875008000.0,
+  "total_flos": 1173425750016000.0,
   "train_batch_size": 26,
   "trial_name": null,
   "trial_params": null