Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a4a0a95ac3cae47977b499fb7f3d5e63750c6aae56e4fdfeb36d68e80ccfae7
+oid sha256:505cb13a465c9411cc4f15a9e86f85848c0b2b5a53badf92ff8e0bbb5ff206f8
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09a1945005fea60223a082b7fbb3a6a75fedd42bcea318d810d089371f192690
+oid sha256:ab234809f7de65a347327bcd5c712cab956b8b7f6a84d571573bf1cc3e3eac41
 size 141053442

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18db6c1bc743d48259413c2026540b18d05325bbab9ad615ffc96744e97a683b
+oid sha256:1d164e3f3bc7b21f6311b4913902d267a8bc53f4a3b4b038f51ba32b099e5f78
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea7ff16b0c30a914eb0d145e3fb06ff9027c6cd2408e766ce8a09accab89a4d
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.21676300578034682,
+  "epoch": 0.43352601156069365,
   "eval_steps": 6,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -222,6 +222,213 @@
       "learning_rate": 0.00010654031292301432,
       "loss": 3.1412,
       "step": 25
+    },
+    {
+      "epoch": 0.2254335260115607,
+      "grad_norm": 7.255655288696289,
+      "learning_rate": 0.0001,
+      "loss": 2.3499,
+      "step": 26
+    },
+    {
+      "epoch": 0.23410404624277456,
+      "grad_norm": 9.42827033996582,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 3.2037,
+      "step": 27
+    },
+    {
+      "epoch": 0.24277456647398843,
+      "grad_norm": 7.624701976776123,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 2.768,
+      "step": 28
+    },
+    {
+      "epoch": 0.2514450867052023,
+      "grad_norm": 7.891088962554932,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 2.3543,
+      "step": 29
+    },
+    {
+      "epoch": 0.26011560693641617,
+      "grad_norm": 6.974014759063721,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 2.1117,
+      "step": 30
+    },
+    {
+      "epoch": 0.26011560693641617,
+      "eval_loss": 2.6875665187835693,
+      "eval_runtime": 15.6483,
+      "eval_samples_per_second": 9.33,
+      "eval_steps_per_second": 2.364,
+      "step": 30
+    },
+    {
+      "epoch": 0.26878612716763006,
+      "grad_norm": 7.1580810546875,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 2.8485,
+      "step": 31
+    },
+    {
+      "epoch": 0.2774566473988439,
+      "grad_norm": 7.447386264801025,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 2.7971,
+      "step": 32
+    },
+    {
+      "epoch": 0.2861271676300578,
+      "grad_norm": 5.977284908294678,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 2.32,
+      "step": 33
+    },
+    {
+      "epoch": 0.2947976878612717,
+      "grad_norm": 6.685746192932129,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 2.5347,
+      "step": 34
+    },
+    {
+      "epoch": 0.30346820809248554,
+      "grad_norm": 12.432933807373047,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 3.2119,
+      "step": 35
+    },
+    {
+      "epoch": 0.31213872832369943,
+      "grad_norm": 7.956794261932373,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 2.2774,
+      "step": 36
+    },
+    {
+      "epoch": 0.31213872832369943,
+      "eval_loss": 2.6305289268493652,
+      "eval_runtime": 15.5922,
+      "eval_samples_per_second": 9.364,
+      "eval_steps_per_second": 2.373,
+      "step": 36
+    },
+    {
+      "epoch": 0.3208092485549133,
+      "grad_norm": 7.3900580406188965,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 2.4076,
+      "step": 37
+    },
+    {
+      "epoch": 0.32947976878612717,
+      "grad_norm": 7.0221710205078125,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 1.9486,
+      "step": 38
+    },
+    {
+      "epoch": 0.33815028901734107,
+      "grad_norm": 7.89264440536499,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 2.6934,
+      "step": 39
+    },
+    {
+      "epoch": 0.3468208092485549,
+      "grad_norm": 7.8453521728515625,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 2.1978,
+      "step": 40
+    },
+    {
+      "epoch": 0.3554913294797688,
+      "grad_norm": 6.693100452423096,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 2.3828,
+      "step": 41
+    },
+    {
+      "epoch": 0.36416184971098264,
+      "grad_norm": 5.916697978973389,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 1.9406,
+      "step": 42
+    },
+    {
+      "epoch": 0.36416184971098264,
+      "eval_loss": 2.5845963954925537,
+      "eval_runtime": 16.1508,
+      "eval_samples_per_second": 9.04,
+      "eval_steps_per_second": 2.291,
+      "step": 42
+    },
+    {
+      "epoch": 0.37283236994219654,
+      "grad_norm": 6.838918685913086,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 2.5254,
+      "step": 43
+    },
+    {
+      "epoch": 0.3815028901734104,
+      "grad_norm": 6.780750274658203,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 2.2767,
+      "step": 44
+    },
+    {
+      "epoch": 0.3901734104046243,
+      "grad_norm": 6.910787582397461,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 2.3037,
+      "step": 45
+    },
+    {
+      "epoch": 0.3988439306358382,
+      "grad_norm": 6.165891170501709,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 2.3262,
+      "step": 46
+    },
+    {
+      "epoch": 0.407514450867052,
+      "grad_norm": 6.632768630981445,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 2.2463,
+      "step": 47
+    },
+    {
+      "epoch": 0.4161849710982659,
+      "grad_norm": 6.605554580688477,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 2.4657,
+      "step": 48
+    },
+    {
+      "epoch": 0.4161849710982659,
+      "eval_loss": 2.575497627258301,
+      "eval_runtime": 15.6673,
+      "eval_samples_per_second": 9.319,
+      "eval_steps_per_second": 2.362,
+      "step": 48
+    },
+    {
+      "epoch": 0.42485549132947975,
+      "grad_norm": 7.213985919952393,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 3.1228,
+      "step": 49
+    },
+    {
+      "epoch": 0.43352601156069365,
+      "grad_norm": 7.434656620025635,
+      "learning_rate": 0.0,
+      "loss": 2.6095,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -236,12 +443,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5536892112076800.0,
+  "total_flos": 1.10737842241536e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null