Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fa4fefa801c4b743aaafc56dc4daa333631d230da93dc9036d0d1d384ab640b
+oid sha256:9fec1a525dc877737a77cdfe34c99ad3e8ca53704a201be3cddcc993fdd81496
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e54d3b42ca119546aece82c44372e3a04d712474bde2971c93422970bd9b8248
+oid sha256:90f41cbed53a9a88d80c618a340a92ced6c02b231a86f6a4e04f7b0ee9b6fd29
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d1e6b7700b4287deb5baa247e83a9c3f267343b661030ec0dad1defff3d9bcf
+oid sha256:156112d017dd7398d552d3a34e39dcb9bc60fdbeb0f1cd906e0742fd48fe2441
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
+oid sha256:212837ccb433e5430b061dc107b19dc09e932e6cfb62a751187d0903b7b0d94e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06201550387596899,
+  "epoch": 0.09302325581395349,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 8.941,
       "eval_steps_per_second": 4.477,
       "step": 50
+    },
+    {
+      "epoch": 0.06325581395348837,
+      "grad_norm": 5.94366979598999,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.6212,
+      "step": 51
+    },
+    {
+      "epoch": 0.06449612403100775,
+      "grad_norm": 6.868124485015869,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 0.4478,
+      "step": 52
+    },
+    {
+      "epoch": 0.06573643410852713,
+      "grad_norm": 2.433790683746338,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 0.0827,
+      "step": 53
+    },
+    {
+      "epoch": 0.06697674418604652,
+      "grad_norm": 3.480111598968506,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.1991,
+      "step": 54
+    },
+    {
+      "epoch": 0.06821705426356589,
+      "grad_norm": 3.1544387340545654,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.3477,
+      "step": 55
+    },
+    {
+      "epoch": 0.06945736434108526,
+      "grad_norm": 3.249091625213623,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 0.4747,
+      "step": 56
+    },
+    {
+      "epoch": 0.07069767441860465,
+      "grad_norm": 2.4261891841888428,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.1281,
+      "step": 57
+    },
+    {
+      "epoch": 0.07193798449612403,
+      "grad_norm": 4.44989538192749,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 0.3445,
+      "step": 58
+    },
+    {
+      "epoch": 0.07317829457364342,
+      "grad_norm": 6.108974933624268,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.5959,
+      "step": 59
+    },
+    {
+      "epoch": 0.07441860465116279,
+      "grad_norm": 3.7152345180511475,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.4014,
+      "step": 60
+    },
+    {
+      "epoch": 0.07565891472868216,
+      "grad_norm": 4.017984390258789,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 0.4625,
+      "step": 61
+    },
+    {
+      "epoch": 0.07689922480620155,
+      "grad_norm": 3.728351593017578,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 0.229,
+      "step": 62
+    },
+    {
+      "epoch": 0.07813953488372093,
+      "grad_norm": 2.818063974380493,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.278,
+      "step": 63
+    },
+    {
+      "epoch": 0.07937984496124031,
+      "grad_norm": 4.94635009765625,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 0.4372,
+      "step": 64
+    },
+    {
+      "epoch": 0.08062015503875969,
+      "grad_norm": 4.1458940505981445,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 0.2506,
+      "step": 65
+    },
+    {
+      "epoch": 0.08186046511627906,
+      "grad_norm": 2.1820178031921387,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.3716,
+      "step": 66
+    },
+    {
+      "epoch": 0.08310077519379845,
+      "grad_norm": 3.0482635498046875,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.2522,
+      "step": 67
+    },
+    {
+      "epoch": 0.08434108527131783,
+      "grad_norm": 2.533395290374756,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 0.1367,
+      "step": 68
+    },
+    {
+      "epoch": 0.08558139534883721,
+      "grad_norm": 5.618951320648193,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.3213,
+      "step": 69
+    },
+    {
+      "epoch": 0.08682170542635659,
+      "grad_norm": 4.922761917114258,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 0.4895,
+      "step": 70
+    },
+    {
+      "epoch": 0.08806201550387596,
+      "grad_norm": 2.011971950531006,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.1357,
+      "step": 71
+    },
+    {
+      "epoch": 0.08930232558139535,
+      "grad_norm": 3.289496421813965,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.2777,
+      "step": 72
+    },
+    {
+      "epoch": 0.09054263565891472,
+      "grad_norm": 2.8057303428649902,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 0.5562,
+      "step": 73
+    },
+    {
+      "epoch": 0.09178294573643411,
+      "grad_norm": 3.366579532623291,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 0.2877,
+      "step": 74
+    },
+    {
+      "epoch": 0.09302325581395349,
+      "grad_norm": 2.185962438583374,
+      "learning_rate": 0.0,
+      "loss": 0.1004,
+      "step": 75
+    },
+    {
+      "epoch": 0.09302325581395349,
+      "eval_loss": 0.40439358353614807,
+      "eval_runtime": 75.8127,
+      "eval_samples_per_second": 8.956,
+      "eval_steps_per_second": 4.485,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -395,12 +578,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7.46010452164608e+16,
+  "total_flos": 1.119015678246912e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null