Training in progress, step 1500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3997e109f067717fd5f809e80f41bce891d8445f976c90d3022e49477ed45df
+oid sha256:d0af6d4f7601d404d24813692db718e4a2d20f4a48d8d3a2a68e00699d0b26e2
 size 2682482800

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4920faf3068b00346c8cda8d82de2a7187b7fbdca6eefe9f18c2b04de64c9ef2
+oid sha256:d167acd227ba225cf9bce9364be165f3171f2eff7a8fde60e11549d6d9cd16bb
 size 5365108834

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e7034a159dfbc62e35de23e4c6fd1b9f4a30b049e2fbd1857b3a8bade788440
+oid sha256:887cd30e708bc2625838e7001c0fa0e942c4fa64e444f4e787d569c422ad050b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc2ced66205bf6a6509c630ed58ad5e3a6e3843df72048f8b326021e9e36307f
+oid sha256:7d259281a955df924ac4ebaa856cdb89459a9b9a13b350ef866b2af10d6d0eea
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:753dcfeefdbe4107c04bfd9f26c44afd642bd34e5d3d0b685a1b7e09f489639e
+oid sha256:f7a835a139362a57ef1920d9ff07a816b3a580439245876e608a4108c26e7ddf
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e87981ec44568bc91dcff3b2572db474da39ce05df9ab33e26b3f375f4eac1b
+oid sha256:d1dfb8149dc214370833c8d5100239e81ec9e9ffa5511208d50605d9d0e710f5
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6956522915b3d6cfb4a36d77fb3f2d3b9a7b7a09c560fa745829757b1d0d295
+oid sha256:e5da8ca094d5fd2cfde37c2e69ed055e71f3022c86dd39598472f504a4eab8b3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07672094673648273,
+  "epoch": 0.1150814201047241,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -147,6 +147,76 @@
       "learning_rate": 9.232775817093756e-05,
       "loss": 67.0964,
       "step": 1000
+    },
+    {
+      "epoch": 0.08055699407330687,
+      "grad_norm": 24.354610443115234,
+      "learning_rate": 9.194414607948443e-05,
+      "loss": 66.8448,
+      "step": 1050
+    },
+    {
+      "epoch": 0.084393041410131,
+      "grad_norm": 32.821502685546875,
+      "learning_rate": 9.156053398803131e-05,
+      "loss": 66.7666,
+      "step": 1100
+    },
+    {
+      "epoch": 0.08822908874695513,
+      "grad_norm": 28.09437370300293,
+      "learning_rate": 9.117692189657818e-05,
+      "loss": 66.4893,
+      "step": 1150
+    },
+    {
+      "epoch": 0.09206513608377927,
+      "grad_norm": 48.216896057128906,
+      "learning_rate": 9.079330980512506e-05,
+      "loss": 66.352,
+      "step": 1200
+    },
+    {
+      "epoch": 0.09590118342060341,
+      "grad_norm": 30.080474853515625,
+      "learning_rate": 9.040969771367193e-05,
+      "loss": 66.2678,
+      "step": 1250
+    },
+    {
+      "epoch": 0.09973723075742755,
+      "grad_norm": 31.63680648803711,
+      "learning_rate": 9.002608562221881e-05,
+      "loss": 66.0015,
+      "step": 1300
+    },
+    {
+      "epoch": 0.10357327809425168,
+      "grad_norm": 64.34364318847656,
+      "learning_rate": 8.964247353076569e-05,
+      "loss": 65.6839,
+      "step": 1350
+    },
+    {
+      "epoch": 0.10740932543107581,
+      "grad_norm": 43.31911087036133,
+      "learning_rate": 8.925886143931257e-05,
+      "loss": 65.4607,
+      "step": 1400
+    },
+    {
+      "epoch": 0.11124537276789996,
+      "grad_norm": 43.40916442871094,
+      "learning_rate": 8.887524934785945e-05,
+      "loss": 65.2276,
+      "step": 1450
+    },
+    {
+      "epoch": 0.1150814201047241,
+      "grad_norm": 27.121234893798828,
+      "learning_rate": 8.849163725640633e-05,
+      "loss": 65.2446,
+      "step": 1500
     }
   ],
   "logging_steps": 50,
@@ -166,7 +236,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7134867976961393e+18,
+  "total_flos": 2.57076562005223e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null