Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46f17de68e3a59b0988437ecd38f041e4a9272fc12756e2c906fa19db60d1d1b
+oid sha256:dd487e4991189b960698eeec21ff4c963e4874531248ee437bf38fb849909a92
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b29e07e92a94fbcc55fb3080d35c134a87e582b67533c94ef3b36e031475f9b
+oid sha256:11289b63983d2e39c1d894880ab1cd4b690f7ddb039908510f9da576c9f882d3
 size 323290986

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d77e18180ba7882742580b93ae3f85f4fc252fca570f89dd579f9f6eb7a5709c
+oid sha256:f1fb5ad79d7259d20d3996bdda5ed526860b9b346c149d424092a2f4732e428d
 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": 0.24311183144246354,
+  "epoch": 0.3241491085899514,
   "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": 2.0281,
       "step": 75
+    },
+    {
+      "epoch": 0.24635332252836303,
+      "grad_norm": 0.5985803604125977,
+      "learning_rate": 3.308693936411421e-06,
+      "loss": 2.1133,
+      "step": 76
+    },
+    {
+      "epoch": 0.24959481361426256,
+      "grad_norm": 0.41972851753234863,
+      "learning_rate": 3.0534162954100264e-06,
+      "loss": 1.9915,
+      "step": 77
+    },
+    {
+      "epoch": 0.25283630470016205,
+      "grad_norm": 0.5193703174591064,
+      "learning_rate": 2.8066019966134907e-06,
+      "loss": 2.1587,
+      "step": 78
+    },
+    {
+      "epoch": 0.2560777957860616,
+      "grad_norm": 0.4557904601097107,
+      "learning_rate": 2.5685517452260566e-06,
+      "loss": 1.9712,
+      "step": 79
+    },
+    {
+      "epoch": 0.2593192868719611,
+      "grad_norm": 0.5277875661849976,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 2.0633,
+      "step": 80
+    },
+    {
+      "epoch": 0.2625607779578606,
+      "grad_norm": 0.3396211862564087,
+      "learning_rate": 2.119892463932781e-06,
+      "loss": 1.8723,
+      "step": 81
+    },
+    {
+      "epoch": 0.2625607779578606,
+      "eval_loss": 2.028590202331543,
+      "eval_runtime": 28.4851,
+      "eval_samples_per_second": 9.128,
+      "eval_steps_per_second": 1.159,
+      "step": 81
+    },
+    {
+      "epoch": 0.26580226904376014,
+      "grad_norm": 0.5749920010566711,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 1.9902,
+      "step": 82
+    },
+    {
+      "epoch": 0.26904376012965964,
+      "grad_norm": 0.5115143060684204,
+      "learning_rate": 1.709624274449584e-06,
+      "loss": 2.0139,
+      "step": 83
+    },
+    {
+      "epoch": 0.27228525121555913,
+      "grad_norm": 0.4236719608306885,
+      "learning_rate": 1.5195190384357405e-06,
+      "loss": 1.8367,
+      "step": 84
+    },
+    {
+      "epoch": 0.2755267423014587,
+      "grad_norm": 0.5460621118545532,
+      "learning_rate": 1.339745962155613e-06,
+      "loss": 2.1697,
+      "step": 85
+    },
+    {
+      "epoch": 0.2787682333873582,
+      "grad_norm": 0.4585734009742737,
+      "learning_rate": 1.1705240714107301e-06,
+      "loss": 1.9294,
+      "step": 86
+    },
+    {
+      "epoch": 0.2820097244732577,
+      "grad_norm": 0.40446731448173523,
+      "learning_rate": 1.012059537008332e-06,
+      "loss": 1.8539,
+      "step": 87
+    },
+    {
+      "epoch": 0.2852512155591572,
+      "grad_norm": 0.5003981590270996,
+      "learning_rate": 8.645454235739903e-07,
+      "loss": 2.1023,
+      "step": 88
+    },
+    {
+      "epoch": 0.2884927066450567,
+      "grad_norm": 0.46330976486206055,
+      "learning_rate": 7.281614543321269e-07,
+      "loss": 1.9343,
+      "step": 89
+    },
+    {
+      "epoch": 0.2917341977309562,
+      "grad_norm": 0.5508167147636414,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 2.2207,
+      "step": 90
+    },
+    {
+      "epoch": 0.2917341977309562,
+      "eval_loss": 2.02809476852417,
+      "eval_runtime": 28.4655,
+      "eval_samples_per_second": 9.134,
+      "eval_steps_per_second": 1.159,
+      "step": 90
+    },
+    {
+      "epoch": 0.29497568881685576,
+      "grad_norm": 0.519679605960846,
+      "learning_rate": 4.894348370484648e-07,
+      "loss": 2.1728,
+      "step": 91
+    },
+    {
+      "epoch": 0.29821717990275526,
+      "grad_norm": 0.33844977617263794,
+      "learning_rate": 3.8738304061681107e-07,
+      "loss": 1.5962,
+      "step": 92
+    },
+    {
+      "epoch": 0.3014586709886548,
+      "grad_norm": 0.4919009208679199,
+      "learning_rate": 2.970427372400353e-07,
+      "loss": 2.3406,
+      "step": 93
+    },
+    {
+      "epoch": 0.3047001620745543,
+      "grad_norm": 0.39633429050445557,
+      "learning_rate": 2.1852399266194312e-07,
+      "loss": 2.0302,
+      "step": 94
+    },
+    {
+      "epoch": 0.3079416531604538,
+      "grad_norm": 0.47110965847969055,
+      "learning_rate": 1.519224698779198e-07,
+      "loss": 1.9712,
+      "step": 95
+    },
+    {
+      "epoch": 0.31118314424635335,
+      "grad_norm": 0.5229762196540833,
+      "learning_rate": 9.731931258429638e-08,
+      "loss": 1.9502,
+      "step": 96
+    },
+    {
+      "epoch": 0.31442463533225284,
+      "grad_norm": 0.48613205552101135,
+      "learning_rate": 5.4781046317267103e-08,
+      "loss": 1.9766,
+      "step": 97
+    },
+    {
+      "epoch": 0.31766612641815234,
+      "grad_norm": 0.5004676580429077,
+      "learning_rate": 2.4359497401758026e-08,
+      "loss": 2.1784,
+      "step": 98
+    },
+    {
+      "epoch": 0.3209076175040519,
+      "grad_norm": 0.4293135702610016,
+      "learning_rate": 6.091729809042379e-09,
+      "loss": 1.9771,
+      "step": 99
+    },
+    {
+      "epoch": 0.3209076175040519,
+      "eval_loss": 2.0276546478271484,
+      "eval_runtime": 28.4861,
+      "eval_samples_per_second": 9.127,
+      "eval_steps_per_second": 1.158,
+      "step": 99
+    },
+    {
+      "epoch": 0.3241491085899514,
+      "grad_norm": 0.62281733751297,
+      "learning_rate": 0.0,
+      "loss": 2.1065,
+      "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": 5.697165350613811e+16,
+  "total_flos": 7.549617887929958e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null