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:d22c53803521c63734819abed6f22a11e4a57aee55c072da1df180e342349e00
+oid sha256:c189fafe0442bc434ea9ee25a4a56257064c42253e459f3dd540662de96ce5b9
 size 216151256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ca75550750d65c363934a763eea6f1db1534075ab6407e082eac8b22bb41286
+oid sha256:37de6c9597255d75f8c05137d693a81e2b4dcd341ef3e99180e30edddf79fa26
 size 432640054

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21b77d4a7d32c9120fea369fe858888ce0fc446e91162b7873cb661c8b5a2b11
+oid sha256:41ef4a6ae8bc773c3d67d43971007c8d98ce5a7438faae96197bb993d7fad29c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:feed204db996a9f7ac3167cc4686c04dccd6605b9b2a7d539da6ff57c605983d
+oid sha256:beccfaf9bab963f178f24d893fd68585ea073339edab1cdcc5698c989a1dd81e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2336448598130841,
+  "epoch": 0.3115264797507788,
   "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": 3.5721239031346067e-06,
       "loss": 3.9235,
       "step": 75
+    },
+    {
+      "epoch": 0.2367601246105919,
+      "grad_norm": 2.258725881576538,
+      "learning_rate": 3.308693936411421e-06,
+      "loss": 3.6753,
+      "step": 76
+    },
+    {
+      "epoch": 0.2398753894080997,
+      "grad_norm": 2.241974115371704,
+      "learning_rate": 3.0534162954100264e-06,
+      "loss": 4.0015,
+      "step": 77
+    },
+    {
+      "epoch": 0.24299065420560748,
+      "grad_norm": 2.302107334136963,
+      "learning_rate": 2.8066019966134907e-06,
+      "loss": 4.2,
+      "step": 78
+    },
+    {
+      "epoch": 0.24610591900311526,
+      "grad_norm": 2.2129664421081543,
+      "learning_rate": 2.5685517452260566e-06,
+      "loss": 3.6274,
+      "step": 79
+    },
+    {
+      "epoch": 0.24922118380062305,
+      "grad_norm": 2.5848774909973145,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 3.7978,
+      "step": 80
+    },
+    {
+      "epoch": 0.2523364485981308,
+      "grad_norm": 1.9426614046096802,
+      "learning_rate": 2.119892463932781e-06,
+      "loss": 3.7625,
+      "step": 81
+    },
+    {
+      "epoch": 0.2523364485981308,
+      "eval_loss": 3.8329532146453857,
+      "eval_runtime": 45.9606,
+      "eval_samples_per_second": 5.875,
+      "eval_steps_per_second": 0.74,
+      "step": 81
+    },
+    {
+      "epoch": 0.2554517133956386,
+      "grad_norm": 2.2936878204345703,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 3.6689,
+      "step": 82
+    },
+    {
+      "epoch": 0.2585669781931464,
+      "grad_norm": 2.0766758918762207,
+      "learning_rate": 1.709624274449584e-06,
+      "loss": 3.7895,
+      "step": 83
+    },
+    {
+      "epoch": 0.2616822429906542,
+      "grad_norm": 2.2929537296295166,
+      "learning_rate": 1.5195190384357405e-06,
+      "loss": 4.0578,
+      "step": 84
+    },
+    {
+      "epoch": 0.26479750778816197,
+      "grad_norm": 2.3588943481445312,
+      "learning_rate": 1.339745962155613e-06,
+      "loss": 3.9087,
+      "step": 85
+    },
+    {
+      "epoch": 0.26791277258566976,
+      "grad_norm": 2.206916332244873,
+      "learning_rate": 1.1705240714107301e-06,
+      "loss": 3.4905,
+      "step": 86
+    },
+    {
+      "epoch": 0.27102803738317754,
+      "grad_norm": 2.3212130069732666,
+      "learning_rate": 1.012059537008332e-06,
+      "loss": 3.9781,
+      "step": 87
+    },
+    {
+      "epoch": 0.27414330218068533,
+      "grad_norm": 2.2561655044555664,
+      "learning_rate": 8.645454235739903e-07,
+      "loss": 4.2637,
+      "step": 88
+    },
+    {
+      "epoch": 0.2772585669781931,
+      "grad_norm": 1.8130618333816528,
+      "learning_rate": 7.281614543321269e-07,
+      "loss": 3.9229,
+      "step": 89
+    },
+    {
+      "epoch": 0.2803738317757009,
+      "grad_norm": 2.447219133377075,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 3.7588,
+      "step": 90
+    },
+    {
+      "epoch": 0.2803738317757009,
+      "eval_loss": 3.8269753456115723,
+      "eval_runtime": 45.9526,
+      "eval_samples_per_second": 5.876,
+      "eval_steps_per_second": 0.74,
+      "step": 90
+    },
+    {
+      "epoch": 0.2834890965732087,
+      "grad_norm": 2.592892646789551,
+      "learning_rate": 4.894348370484648e-07,
+      "loss": 3.6204,
+      "step": 91
+    },
+    {
+      "epoch": 0.2866043613707165,
+      "grad_norm": 2.100886583328247,
+      "learning_rate": 3.8738304061681107e-07,
+      "loss": 3.7326,
+      "step": 92
+    },
+    {
+      "epoch": 0.2897196261682243,
+      "grad_norm": 2.104876756668091,
+      "learning_rate": 2.970427372400353e-07,
+      "loss": 3.8676,
+      "step": 93
+    },
+    {
+      "epoch": 0.29283489096573206,
+      "grad_norm": 2.2233452796936035,
+      "learning_rate": 2.1852399266194312e-07,
+      "loss": 3.9545,
+      "step": 94
+    },
+    {
+      "epoch": 0.29595015576323985,
+      "grad_norm": 2.0933141708374023,
+      "learning_rate": 1.519224698779198e-07,
+      "loss": 3.9269,
+      "step": 95
+    },
+    {
+      "epoch": 0.29906542056074764,
+      "grad_norm": 2.0308425426483154,
+      "learning_rate": 9.731931258429638e-08,
+      "loss": 3.385,
+      "step": 96
+    },
+    {
+      "epoch": 0.30218068535825543,
+      "grad_norm": 2.177314519882202,
+      "learning_rate": 5.4781046317267103e-08,
+      "loss": 3.4789,
+      "step": 97
+    },
+    {
+      "epoch": 0.3052959501557632,
+      "grad_norm": 2.3775551319122314,
+      "learning_rate": 2.4359497401758026e-08,
+      "loss": 3.9702,
+      "step": 98
+    },
+    {
+      "epoch": 0.308411214953271,
+      "grad_norm": 2.284379720687866,
+      "learning_rate": 6.091729809042379e-09,
+      "loss": 3.7161,
+      "step": 99
+    },
+    {
+      "epoch": 0.308411214953271,
+      "eval_loss": 3.825807809829712,
+      "eval_runtime": 45.9358,
+      "eval_samples_per_second": 5.878,
+      "eval_steps_per_second": 0.74,
+      "step": 99
+    },
+    {
+      "epoch": 0.3115264797507788,
+      "grad_norm": 2.239882230758667,
+      "learning_rate": 0.0,
+      "loss": 3.9464,
+      "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": 6.17709406519296e+16,
+  "total_flos": 8.23612542025728e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null