Training in progress, step 70, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8c439be4803744433b47ca728c7a63d53901013c38bf5d7cf39d918f132b1ee
+oid sha256:cbb7a2a016a29e85a73a1b83fe04b79c45ab830ca66b55dcd4e6288bc339313c
 size 3299862016

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8a46f192c7007ad6ce5da6988c91bee9948ab2738cddfc8019e1fb41aa163d0
+oid sha256:5070700dbd67e0d35545a8dd8a734e90f49b9574f8e0397bae234b11da431263
 size 3300016907

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91ca5a4bc45dfb99eea6c6cd6eb5d8a912a32e73758c41c0b0f334f0ec0c5d35
+oid sha256:5a135c944323c853219eae2b546147a5feb5d615450aab3e93244e542a70e149
 size 1401

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0002667265319549499,
+  "epoch": 0.00031118095394744153,
   "eval_steps": 500,
-  "global_step": 60,
+  "global_step": 70,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -428,6 +428,76 @@
       "learning_rate": 1.311417108436413e-08,
       "loss": 11.2566,
       "step": 60
+    },
+    {
+      "epoch": 0.00027117197415419905,
+      "grad_norm": 13.6875,
+      "learning_rate": 1.3336445170539793e-08,
+      "loss": 11.2566,
+      "step": 61
+    },
+    {
+      "epoch": 0.0002756174163534482,
+      "grad_norm": 15.0625,
+      "learning_rate": 1.3558719256715456e-08,
+      "loss": 11.2535,
+      "step": 62
+    },
+    {
+      "epoch": 0.0002800628585526974,
+      "grad_norm": 18.625,
+      "learning_rate": 1.3780993342891119e-08,
+      "loss": 11.2911,
+      "step": 63
+    },
+    {
+      "epoch": 0.00028450830075194656,
+      "grad_norm": 18.25,
+      "learning_rate": 1.4003267429066783e-08,
+      "loss": 11.2483,
+      "step": 64
+    },
+    {
+      "epoch": 0.00028895374295119573,
+      "grad_norm": 18.125,
+      "learning_rate": 1.4225541515242446e-08,
+      "loss": 11.2932,
+      "step": 65
+    },
+    {
+      "epoch": 0.0002933991851504449,
+      "grad_norm": 19.875,
+      "learning_rate": 1.4447815601418109e-08,
+      "loss": 11.228,
+      "step": 66
+    },
+    {
+      "epoch": 0.000297844627349694,
+      "grad_norm": 14.9375,
+      "learning_rate": 1.4670089687593772e-08,
+      "loss": 11.2736,
+      "step": 67
+    },
+    {
+      "epoch": 0.0003022900695489432,
+      "grad_norm": 11.8125,
+      "learning_rate": 1.4892363773769438e-08,
+      "loss": 11.2563,
+      "step": 68
+    },
+    {
+      "epoch": 0.00030673551174819236,
+      "grad_norm": 24.875,
+      "learning_rate": 1.51146378599451e-08,
+      "loss": 11.2704,
+      "step": 69
+    },
+    {
+      "epoch": 0.00031118095394744153,
+      "grad_norm": 15.25,
+      "learning_rate": 1.5336911946120762e-08,
+      "loss": 11.2611,
+      "step": 70
     }
   ],
   "logging_steps": 1,
@@ -447,7 +517,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4674673575198720.0,
+  "total_flos": 5453785837731840.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null