Training in progress, step 126, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:121983274dff80eb5f14c755257724700d2d56e115cc300d0316f914d3cb7dee
+oid sha256:aadd79cb0ce90a3800ba84eddb5d6ed311601f6907fd8577721c4a48d11c900a
 size 201892112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5e2df5660b367f6f036c08934da668f1270a0be7f47fa9b46e2cae168bcf555
+oid sha256:3369db71b47a6b28d8af870490f2fffae251fdfc9b2ec04d614352e035cb1c3a
 size 102864548

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7074cec2061417cedcea0f1edca671f4979b23051157d7011cc5e12489f9fe90
+oid sha256:9e19d88c5ee8945747e0c8f00ae8f30f12218b1bee6b5d59ad749865193f9388
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2df224011d0e75c4a97901f6c1b2930bba4bc3a9aa7c877e6c91e796bec6013f
+oid sha256:e00328545513b592b6bf311a002e087bb048e374276594cf37ee8782d28887fc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01760821716801174,
+  "epoch": 0.02641232575201761,
   "eval_steps": 42,
-  "global_step": 84,
+  "global_step": 126,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -227,6 +227,112 @@
       "eval_samples_per_second": 48.68,
       "eval_steps_per_second": 6.089,
       "step": 84
+    },
+    {
+      "epoch": 0.0182370820668693,
+      "grad_norm": 0.3466218411922455,
+      "learning_rate": 9.40297765928369e-05,
+      "loss": 1.181,
+      "step": 87
+    },
+    {
+      "epoch": 0.018865946965726865,
+      "grad_norm": 0.3219515085220337,
+      "learning_rate": 9.356593520616948e-05,
+      "loss": 1.1236,
+      "step": 90
+    },
+    {
+      "epoch": 0.019494811864584426,
+      "grad_norm": 0.35251516103744507,
+      "learning_rate": 9.308597683653975e-05,
+      "loss": 1.1749,
+      "step": 93
+    },
+    {
+      "epoch": 0.020123676763441987,
+      "grad_norm": 0.3366820514202118,
+      "learning_rate": 9.259007904196023e-05,
+      "loss": 1.1411,
+      "step": 96
+    },
+    {
+      "epoch": 0.020752541662299548,
+      "grad_norm": 0.3501774072647095,
+      "learning_rate": 9.207842527714767e-05,
+      "loss": 1.122,
+      "step": 99
+    },
+    {
+      "epoch": 0.021381406561157112,
+      "grad_norm": 0.3260366916656494,
+      "learning_rate": 9.155120482565521e-05,
+      "loss": 1.1032,
+      "step": 102
+    },
+    {
+      "epoch": 0.022010271460014674,
+      "grad_norm": 0.3130464255809784,
+      "learning_rate": 9.10086127298478e-05,
+      "loss": 1.1025,
+      "step": 105
+    },
+    {
+      "epoch": 0.022639136358872235,
+      "grad_norm": 0.3319336473941803,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.1279,
+      "step": 108
+    },
+    {
+      "epoch": 0.0232680012577298,
+      "grad_norm": 0.3683924973011017,
+      "learning_rate": 8.987812213377424e-05,
+      "loss": 1.1384,
+      "step": 111
+    },
+    {
+      "epoch": 0.02389686615658736,
+      "grad_norm": 0.3043256998062134,
+      "learning_rate": 8.929064185241213e-05,
+      "loss": 1.106,
+      "step": 114
+    },
+    {
+      "epoch": 0.02452573105544492,
+      "grad_norm": 0.3852984607219696,
+      "learning_rate": 8.868862620982534e-05,
+      "loss": 1.123,
+      "step": 117
+    },
+    {
+      "epoch": 0.025154595954302483,
+      "grad_norm": 0.36246711015701294,
+      "learning_rate": 8.807229791845673e-05,
+      "loss": 1.1248,
+      "step": 120
+    },
+    {
+      "epoch": 0.025783460853160047,
+      "grad_norm": 0.3592873215675354,
+      "learning_rate": 8.744188498563641e-05,
+      "loss": 1.0983,
+      "step": 123
+    },
+    {
+      "epoch": 0.02641232575201761,
+      "grad_norm": 0.3461982309818268,
+      "learning_rate": 8.679762062923175e-05,
+      "loss": 1.1211,
+      "step": 126
+    },
+    {
+      "epoch": 0.02641232575201761,
+      "eval_loss": 1.1246975660324097,
+      "eval_runtime": 165.051,
+      "eval_samples_per_second": 48.682,
+      "eval_steps_per_second": 6.089,
+      "step": 126
     }
   ],
   "logging_steps": 3,
@@ -246,7 +352,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7918441960767488e+16,
+  "total_flos": 2.687766294115123e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null