Training in progress, step 13500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84ffb6564333bec2f290dbb25cc2aa16322f854baa8d4d551f3c98e898121f1a
+oid sha256:1d7e7ce5d8087ead3443b4f08e582b8deb0371c597dc0bcefa92b27b47cf757b
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55950639d5a01737cdced1ff8ae565003480c956e54966fe29dbcc5ee832bbe0
+oid sha256:9b3343f5795c77c59b4597ad652cbd699824ac18f885e075e189a3d182b5959e
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ede19b1f06f575564a160b0c17fcb5315d8660261b38069d03c83f6d06084b12
+oid sha256:134eebb9d67a08338a927439b5399d422ef15da51b7ad38136806c07d685a893
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ed905996f8c375ddf1e71a02110476c5d9bb4d922dca340182e086437e4a3a1
+oid sha256:2f1ce7c9ab70607ae470f91da12ff0d4b8f6d4eec2f38f9df9861eec2ba77599
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.08158940076828003,
   "best_model_checkpoint": "./fine-tuned/checkpoint-12500",
-  "epoch": 2.08,
+  "epoch": 2.16,
   "eval_steps": 500,
-  "global_step": 13000,
+  "global_step": 13500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2035,6 +2035,84 @@
       "eval_samples_per_second": 17.094,
       "eval_steps_per_second": 2.137,
       "step": 13000
+    },
+    {
+      "epoch": 2.088,
+      "grad_norm": 7875.97900390625,
+      "learning_rate": 9.12e-06,
+      "loss": 0.049,
+      "step": 13050
+    },
+    {
+      "epoch": 2.096,
+      "grad_norm": 6825.78076171875,
+      "learning_rate": 9.04e-06,
+      "loss": 0.0465,
+      "step": 13100
+    },
+    {
+      "epoch": 2.104,
+      "grad_norm": 5515.30322265625,
+      "learning_rate": 8.96e-06,
+      "loss": 0.0535,
+      "step": 13150
+    },
+    {
+      "epoch": 2.112,
+      "grad_norm": 8940.48828125,
+      "learning_rate": 8.88e-06,
+      "loss": 0.0564,
+      "step": 13200
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 5110.7119140625,
+      "learning_rate": 8.8e-06,
+      "loss": 0.0509,
+      "step": 13250
+    },
+    {
+      "epoch": 2.128,
+      "grad_norm": 8984.7353515625,
+      "learning_rate": 8.720000000000001e-06,
+      "loss": 0.0479,
+      "step": 13300
+    },
+    {
+      "epoch": 2.136,
+      "grad_norm": 8438.55078125,
+      "learning_rate": 8.64e-06,
+      "loss": 0.0502,
+      "step": 13350
+    },
+    {
+      "epoch": 2.144,
+      "grad_norm": 5724.0849609375,
+      "learning_rate": 8.56e-06,
+      "loss": 0.0501,
+      "step": 13400
+    },
+    {
+      "epoch": 2.152,
+      "grad_norm": 7649.28955078125,
+      "learning_rate": 8.48e-06,
+      "loss": 0.0569,
+      "step": 13450
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 8429.0166015625,
+      "learning_rate": 8.400000000000001e-06,
+      "loss": 0.053,
+      "step": 13500
+    },
+    {
+      "epoch": 2.16,
+      "eval_loss": 0.08213882148265839,
+      "eval_runtime": 116.6956,
+      "eval_samples_per_second": 17.139,
+      "eval_steps_per_second": 2.142,
+      "step": 13500
     }
   ],
   "logging_steps": 50,
@@ -2054,7 +2132,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.333162061824e+16,
+  "total_flos": 6.576745218048e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null