Training in progress, step 8000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b597ae305154571a9cf0fc318fd2f02878b6fc2337475a4dbbe0703d844213e4
+oid sha256:4cbfbd0f6a07b835e4eb96ae97dd49eff870ad88d6be40d3bd1e0357be8624f8
 size 471641972

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85bb5c5574de9da9d3ba8e7a266718161ca8465cc2f476d079631453bb47755d
+oid sha256:d2245879460433ceb7eb7c5b19fed96d125ec36ce0d53f2cd06f9d87c1a467ab
 size 943408715

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e245b446c6f11ba7b61a7b70b2e26db93445e984c29a565ba9fa0a4c06c6c7e
+oid sha256:04ed82d1fdf30f41ed12aad05e55898e36a9e89c5860f5a9745500b3b0bce109
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6af8329711dde815df15cc29a7be4297f7e74c40a36d0acc98aace42529f4f55
+oid sha256:d4da13d0d238bcfbcaf7c2d149fc9e058944471070eba242db234d5d3e151f20
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aded58ff1e996ada0739166f06f8ea3e063c8206207381ac3ffc60d844872983
+oid sha256:acfed49c8551f776696d2cfe4ff48e27d2dd05686444ac96aaac243eb30eaf75
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7106418618816781,
+  "epoch": 0.812162127864775,
   "eval_steps": 500,
-  "global_step": 7000,
+  "global_step": 8000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -505,6 +505,76 @@
       "learning_rate": 3.0476597563581964e-05,
       "loss": 2.0123,
       "step": 7000
+    },
+    {
+      "epoch": 0.7207938884799878,
+      "grad_norm": 6.965139865875244,
+      "learning_rate": 2.9407993160931823e-05,
+      "loss": 2.0076,
+      "step": 7100
+    },
+    {
+      "epoch": 0.7309459150782975,
+      "grad_norm": 6.2129411697387695,
+      "learning_rate": 2.8339388758281688e-05,
+      "loss": 2.0221,
+      "step": 7200
+    },
+    {
+      "epoch": 0.7410979416766071,
+      "grad_norm": 6.450573921203613,
+      "learning_rate": 2.7270784355631546e-05,
+      "loss": 1.9899,
+      "step": 7300
+    },
+    {
+      "epoch": 0.7512499682749169,
+      "grad_norm": 6.273707866668701,
+      "learning_rate": 2.6202179952981408e-05,
+      "loss": 1.9801,
+      "step": 7400
+    },
+    {
+      "epoch": 0.7614019948732266,
+      "grad_norm": 6.587959289550781,
+      "learning_rate": 2.5133575550331266e-05,
+      "loss": 1.973,
+      "step": 7500
+    },
+    {
+      "epoch": 0.7715540214715363,
+      "grad_norm": 7.1678948402404785,
+      "learning_rate": 2.4064971147681128e-05,
+      "loss": 2.0192,
+      "step": 7600
+    },
+    {
+      "epoch": 0.7817060480698459,
+      "grad_norm": 6.3077874183654785,
+      "learning_rate": 2.299636674503099e-05,
+      "loss": 1.9815,
+      "step": 7700
+    },
+    {
+      "epoch": 0.7918580746681556,
+      "grad_norm": 7.233158111572266,
+      "learning_rate": 2.192776234238085e-05,
+      "loss": 2.0093,
+      "step": 7800
+    },
+    {
+      "epoch": 0.8020101012664653,
+      "grad_norm": 6.688365459442139,
+      "learning_rate": 2.0859157939730713e-05,
+      "loss": 1.9382,
+      "step": 7900
+    },
+    {
+      "epoch": 0.812162127864775,
+      "grad_norm": 6.085184574127197,
+      "learning_rate": 1.9790553537080574e-05,
+      "loss": 1.967,
+      "step": 8000
     }
   ],
   "logging_steps": 100,
@@ -524,7 +594,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3807757501036032.0,
+  "total_flos": 4349680792659456.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null