Training in progress, step 12000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec779206cf54d6ec2f38c65a076b00fc932c67753a52bdb7f8e2048ec7b5aa72
+oid sha256:6989d08304817f7eda2a41817fe6fdf1039613dcc5ce63bc28b05cebb5b0a729
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4aa8d2bcba67d1c3e0e255eaa792d3f5d5d742e9420328ca489a27ffc5e297e
+oid sha256:9ef2622b356cc24fc03d43081c989231e41a9f98afae1477feeac80752fcbe27
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cdc0a7876cc40e108078f019affd5e2fa19bd7432063cc097ebdc6e0c9f6bc0
+oid sha256:25c75df0b33157e12f11389fab2a782cb08091622aab636059c475b184fac12c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06badf22ccd7f837423b8b17ce3c2141862926d038c21fb5506d2929cbbb4d8f
+oid sha256:4ba896b8260293f6060945e9d4b6d72d879757324e56407782c7dd941c44937b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.08293735980987549,
-  "best_model_checkpoint": "./fine-tuned/checkpoint-11500",
-  "epoch": 0.92,
+  "best_metric": 0.082674041390419,
+  "best_model_checkpoint": "./fine-tuned/checkpoint-12000",
+  "epoch": 0.96,
   "eval_steps": 500,
-  "global_step": 11500,
+  "global_step": 12000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1801,6 +1801,84 @@
       "eval_samples_per_second": 22.711,
       "eval_steps_per_second": 5.678,
       "step": 11500
+    },
+    {
+      "epoch": 0.924,
+      "grad_norm": 0.12364531308412552,
+      "learning_rate": 1.61424e-05,
+      "loss": 0.0624,
+      "step": 11550
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 0.15913207828998566,
+      "learning_rate": 1.60824e-05,
+      "loss": 0.061,
+      "step": 11600
+    },
+    {
+      "epoch": 0.932,
+      "grad_norm": 0.16585472226142883,
+      "learning_rate": 1.60224e-05,
+      "loss": 0.066,
+      "step": 11650
+    },
+    {
+      "epoch": 0.936,
+      "grad_norm": 0.13831599056720734,
+      "learning_rate": 1.59624e-05,
+      "loss": 0.0578,
+      "step": 11700
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.1819075047969818,
+      "learning_rate": 1.59024e-05,
+      "loss": 0.0593,
+      "step": 11750
+    },
+    {
+      "epoch": 0.944,
+      "grad_norm": 0.16260235011577606,
+      "learning_rate": 1.58424e-05,
+      "loss": 0.0647,
+      "step": 11800
+    },
+    {
+      "epoch": 0.948,
+      "grad_norm": 0.1420051008462906,
+      "learning_rate": 1.57824e-05,
+      "loss": 0.0556,
+      "step": 11850
+    },
+    {
+      "epoch": 0.952,
+      "grad_norm": 0.17357395589351654,
+      "learning_rate": 1.57224e-05,
+      "loss": 0.0585,
+      "step": 11900
+    },
+    {
+      "epoch": 0.956,
+      "grad_norm": 0.1465808004140854,
+      "learning_rate": 1.56624e-05,
+      "loss": 0.0633,
+      "step": 11950
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.18425939977169037,
+      "learning_rate": 1.56024e-05,
+      "loss": 0.061,
+      "step": 12000
+    },
+    {
+      "epoch": 0.96,
+      "eval_loss": 0.082674041390419,
+      "eval_runtime": 88.0509,
+      "eval_samples_per_second": 22.714,
+      "eval_steps_per_second": 5.679,
+      "step": 12000
     }
   ],
   "logging_steps": 50,
@@ -1820,7 +1898,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.801206296576e+16,
+  "total_flos": 2.922997874688e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null