Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61ba3fe3cb2475b94657ce9e32267038b5e85ee9277ae09c2b3996fb51231f25
+oid sha256:00ebbe0c1fad7f1197b3c4585c43c72b7c0e5e70b28eb72398e65715c08eebd0
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b778c88601b7ad8df5af534988bdfb03314562213289eae19e14ec6ef6377b90
+oid sha256:e5c7a7ec4da58d5fb29e442ec112bd0194039a05e4e2f204d2039d52f19b6d7e
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:408e56684290fc2d4d62af6818d9eed799690d481ec8a8ead29730102632763f
+oid sha256:faac1656e758e8dc521d5b3ce272931901186027e782eb031f8a28a6467d6ac1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
+oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0018593120545398203,
+  "epoch": 0.002479082739386427,
   "eval_steps": 9,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -604,6 +604,205 @@
       "learning_rate": 1.7860619515673033e-05,
       "loss": 0.0,
       "step": 75
+    },
+    {
+      "epoch": 0.0018841028819336846,
+      "grad_norm": 4.014698028564453,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.3185,
+      "step": 76
+    },
+    {
+      "epoch": 0.0019088937093275488,
+      "grad_norm": 0.015278141014277935,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.0002,
+      "step": 77
+    },
+    {
+      "epoch": 0.0019336845367214132,
+      "grad_norm": 0.001542494399473071,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.0,
+      "step": 78
+    },
+    {
+      "epoch": 0.0019584753641152773,
+      "grad_norm": 0.009143107570707798,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.0002,
+      "step": 79
+    },
+    {
+      "epoch": 0.0019832661915091415,
+      "grad_norm": 0.020335160195827484,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0003,
+      "step": 80
+    },
+    {
+      "epoch": 0.002008057018903006,
+      "grad_norm": 0.0007250762428157032,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.0,
+      "step": 81
+    },
+    {
+      "epoch": 0.002008057018903006,
+      "eval_loss": 0.006126614287495613,
+      "eval_runtime": 3463.0899,
+      "eval_samples_per_second": 9.809,
+      "eval_steps_per_second": 1.226,
+      "step": 81
+    },
+    {
+      "epoch": 0.00203284784629687,
+      "grad_norm": 0.006182220298796892,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0001,
+      "step": 82
+    },
+    {
+      "epoch": 0.0020576386736907344,
+      "grad_norm": 0.0013380810851231217,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.0,
+      "step": 83
+    },
+    {
+      "epoch": 0.0020824295010845985,
+      "grad_norm": 0.010265359655022621,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.0001,
+      "step": 84
+    },
+    {
+      "epoch": 0.002107220328478463,
+      "grad_norm": 0.0020443315152078867,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0,
+      "step": 85
+    },
+    {
+      "epoch": 0.0021320111558723273,
+      "grad_norm": 0.04433085024356842,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.0005,
+      "step": 86
+    },
+    {
+      "epoch": 0.0021568019832661914,
+      "grad_norm": 0.006436903961002827,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.0,
+      "step": 87
+    },
+    {
+      "epoch": 0.0021815928106600556,
+      "grad_norm": 0.0021947952918708324,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.0,
+      "step": 88
+    },
+    {
+      "epoch": 0.00220638363805392,
+      "grad_norm": 0.0019828679505735636,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.0,
+      "step": 89
+    },
+    {
+      "epoch": 0.0022311744654477843,
+      "grad_norm": 0.008004413917660713,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0001,
+      "step": 90
+    },
+    {
+      "epoch": 0.0022311744654477843,
+      "eval_loss": 0.004822232760488987,
+      "eval_runtime": 3464.2169,
+      "eval_samples_per_second": 9.806,
+      "eval_steps_per_second": 1.226,
+      "step": 90
+    },
+    {
+      "epoch": 0.0022559652928416485,
+      "grad_norm": 0.001327146659605205,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0,
+      "step": 91
+    },
+    {
+      "epoch": 0.002280756120235513,
+      "grad_norm": 0.0026161230634897947,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.0,
+      "step": 92
+    },
+    {
+      "epoch": 0.002305546947629377,
+      "grad_norm": 0.006191144231706858,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.0001,
+      "step": 93
+    },
+    {
+      "epoch": 0.0023303377750232414,
+      "grad_norm": 0.0058226496912539005,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.0001,
+      "step": 94
+    },
+    {
+      "epoch": 0.0023551286024171055,
+      "grad_norm": 0.002520521404221654,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0001,
+      "step": 95
+    },
+    {
+      "epoch": 0.00237991942981097,
+      "grad_norm": 0.002172236330807209,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.0,
+      "step": 96
+    },
+    {
+      "epoch": 0.0024047102572048343,
+      "grad_norm": 0.002350907539948821,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.0,
+      "step": 97
+    },
+    {
+      "epoch": 0.0024295010845986984,
+      "grad_norm": 0.0026973439380526543,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.0001,
+      "step": 98
+    },
+    {
+      "epoch": 0.0024542919119925626,
+      "grad_norm": 0.07727763801813126,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.0013,
+      "step": 99
+    },
+    {
+      "epoch": 0.0024542919119925626,
+      "eval_loss": 0.0047203367576003075,
+      "eval_runtime": 3466.2129,
+      "eval_samples_per_second": 9.8,
+      "eval_steps_per_second": 1.225,
+      "step": 99
+    },
+    {
+      "epoch": 0.002479082739386427,
+      "grad_norm": 0.003464354667812586,
+      "learning_rate": 0.0,
+      "loss": 0.0001,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -618,12 +817,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.9582058766336e+16,
+  "total_flos": 6.6109411688448e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null