Upload folder using huggingface_hub

checkpoint-latest/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03190bb45309bbfedccad7959d6dd1878e0a3a2c49476630690e4b0b715ba571
+oid sha256:ef513511cab07aae2229c81db3abdc654a0b3295a3c2d11cbd3d6499af06ee82
 size 62293080

checkpoint-latest/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08db5c721a857b9e376429cfbe60e90ff49062398fa0ce0ed683edf407f96d3c
+oid sha256:28fc9a9bbe9b73a2b142749dd94f1bfc0455d15809207712e61bb52c170e192c
 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/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47578247ee117cf4bc0a0c2af4d329dc3c61e90f1c21bdab88f7e138719d3e25
+oid sha256:09920373f9c73ff341f9b497a1508313129ce162304c3799289a6c23932f7385
 size 1383

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": 166.359,
       "eval_steps_per_second": 6.401,
       "step": 1000
+    },
+    {
+      "epoch": 0.1979588245644906,
+      "grad_norm": 0.7378321290016174,
+      "learning_rate": 0.0002802217138835122,
+      "loss": 3.1179,
+      "step": 1125
+    },
+    {
+      "epoch": 0.21995424951610065,
+      "grad_norm": 0.861381471157074,
+      "learning_rate": 0.0002780221713883512,
+      "loss": 3.103,
+      "step": 1250
+    },
+    {
+      "epoch": 0.2419496744677107,
+      "grad_norm": 0.8002694249153137,
+      "learning_rate": 0.0002758226288931902,
+      "loss": 3.1028,
+      "step": 1375
+    },
+    {
+      "epoch": 0.26394509941932076,
+      "grad_norm": 0.6079952120780945,
+      "learning_rate": 0.0002736230863980292,
+      "loss": 3.0921,
+      "step": 1500
+    },
+    {
+      "epoch": 0.26394509941932076,
+      "eval_loss": 2.646458864212036,
+      "eval_runtime": 59.2373,
+      "eval_samples_per_second": 166.28,
+      "eval_steps_per_second": 6.398,
+      "step": 1500
+    },
+    {
+      "epoch": 0.28594052437093087,
+      "grad_norm": 0.9203604459762573,
+      "learning_rate": 0.0002714235439028682,
+      "loss": 3.1046,
+      "step": 1625
+    },
+    {
+      "epoch": 0.3079359493225409,
+      "grad_norm": 1.0269505977630615,
+      "learning_rate": 0.00026922400140770716,
+      "loss": 3.0836,
+      "step": 1750
+    },
+    {
+      "epoch": 0.329931374274151,
+      "grad_norm": 0.7157150506973267,
+      "learning_rate": 0.0002670244589125462,
+      "loss": 3.095,
+      "step": 1875
+    },
+    {
+      "epoch": 0.35192679922576103,
+      "grad_norm": 0.6990401148796082,
+      "learning_rate": 0.00026482491641738516,
+      "loss": 3.083,
+      "step": 2000
+    },
+    {
+      "epoch": 0.35192679922576103,
+      "eval_loss": 2.6299610137939453,
+      "eval_runtime": 58.9681,
+      "eval_samples_per_second": 167.039,
+      "eval_steps_per_second": 6.427,
+      "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