Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96ec397337ef77eee530f814d539f33c943981a4bd4a3e971d62e88c517edc20
+oid sha256:2fc862ae40e6c4de4708daeb34a63f835033e18a3cba6eab91ccc4ae67068d6f
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03ba80e9a2e3576d7a7a6a199d80a9002362887a78cc0ee5d6b707736c0a99f2
+oid sha256:3bdefc6385ae67d9424b3aaa4dc01a5d36bcdebfbf4687207c4e9108afcba51b
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5dea239019adda822b018dfbb0e0dab7e33e9d3cdf695575c23b4f6459af0f2
+oid sha256:93e6e3c618d6ae8d5654d7ef91d26c72508ddd6bfb5680a8d2e1a858ba9729c7
 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": 0.13740982480247338,
+  "epoch": 0.20611473720371007,
   "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": 4.128,
       "eval_steps_per_second": 2.071,
       "step": 50
+    },
+    {
+      "epoch": 0.14015802129852284,
+      "grad_norm": 126.30210876464844,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 28.9496,
+      "step": 51
+    },
+    {
+      "epoch": 0.1429062177945723,
+      "grad_norm": 167.9775390625,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 30.9349,
+      "step": 52
+    },
+    {
+      "epoch": 0.1456544142906218,
+      "grad_norm": 169.74281311035156,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 32.6468,
+      "step": 53
+    },
+    {
+      "epoch": 0.14840261078667125,
+      "grad_norm": 146.56332397460938,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 26.633,
+      "step": 54
+    },
+    {
+      "epoch": 0.1511508072827207,
+      "grad_norm": 125.53800201416016,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 26.7496,
+      "step": 55
+    },
+    {
+      "epoch": 0.1538990037787702,
+      "grad_norm": 123.63423919677734,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 24.4147,
+      "step": 56
+    },
+    {
+      "epoch": 0.15664720027481965,
+      "grad_norm": 114.20004272460938,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 20.9682,
+      "step": 57
+    },
+    {
+      "epoch": 0.1593953967708691,
+      "grad_norm": 103.33562469482422,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 21.909,
+      "step": 58
+    },
+    {
+      "epoch": 0.16214359326691857,
+      "grad_norm": 92.96592712402344,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 25.0873,
+      "step": 59
+    },
+    {
+      "epoch": 0.16489178976296806,
+      "grad_norm": 62.3299446105957,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 18.7571,
+      "step": 60
+    },
+    {
+      "epoch": 0.16763998625901752,
+      "grad_norm": 86.38172149658203,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 21.9001,
+      "step": 61
+    },
+    {
+      "epoch": 0.17038818275506698,
+      "grad_norm": 74.97166442871094,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 20.1402,
+      "step": 62
+    },
+    {
+      "epoch": 0.17313637925111647,
+      "grad_norm": 73.96630859375,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 18.3307,
+      "step": 63
+    },
+    {
+      "epoch": 0.17588457574716593,
+      "grad_norm": 52.179691314697266,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 16.4085,
+      "step": 64
+    },
+    {
+      "epoch": 0.1786327722432154,
+      "grad_norm": 64.35760498046875,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 17.4018,
+      "step": 65
+    },
+    {
+      "epoch": 0.18138096873926485,
+      "grad_norm": 53.43449020385742,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 17.7936,
+      "step": 66
+    },
+    {
+      "epoch": 0.18412916523531433,
+      "grad_norm": 63.03330993652344,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 19.4953,
+      "step": 67
+    },
+    {
+      "epoch": 0.1868773617313638,
+      "grad_norm": 56.1005744934082,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 19.2624,
+      "step": 68
+    },
+    {
+      "epoch": 0.18962555822741325,
+      "grad_norm": 58.30370330810547,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 20.5131,
+      "step": 69
+    },
+    {
+      "epoch": 0.19237375472346271,
+      "grad_norm": 140.84652709960938,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 20.3344,
+      "step": 70
+    },
+    {
+      "epoch": 0.1951219512195122,
+      "grad_norm": 80.73768615722656,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 21.1099,
+      "step": 71
+    },
+    {
+      "epoch": 0.19787014771556166,
+      "grad_norm": 60.10904312133789,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 19.9792,
+      "step": 72
+    },
+    {
+      "epoch": 0.20061834421161112,
+      "grad_norm": 60.41555404663086,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 19.814,
+      "step": 73
+    },
+    {
+      "epoch": 0.2033665407076606,
+      "grad_norm": 63.792991638183594,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 17.6842,
+      "step": 74
+    },
+    {
+      "epoch": 0.20611473720371007,
+      "grad_norm": 60.221309661865234,
+      "learning_rate": 0.0,
+      "loss": 19.4464,
+      "step": 75
+    },
+    {
+      "epoch": 0.20611473720371007,
+      "eval_loss": 2.4529173374176025,
+      "eval_runtime": 74.3432,
+      "eval_samples_per_second": 4.129,
+      "eval_steps_per_second": 2.071,
+      "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": 7.07252667285504e+16,
+  "total_flos": 1.060879000928256e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null