Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3db4cec11cb96d0460bb12cee61072ce85dc9c15b08ea79ff3189ee41f96257a
+oid sha256:58c8272a193ab6bf652435dc335b346f7d20558315e220973890a84ee4d5c659
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c60385e8608bfc28d3eff1f686b5250b2f977ce329db2291a75b9c71be23b73f
+oid sha256:b30db81db7037f82e672a56c732c9d28e4227d5554f0e70dd499d59d0c2c7830
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cad2658200f2482b7574bdc57c18294b67c90589354a1df1f50b18ca492e76c
+oid sha256:23b292c0efb28eea88c002c7c382d68ce9c4cd641c1f3fb777ab6b43a2d8a19d
 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": 0.30120481927710846,
+  "epoch": 0.40160642570281124,
   "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": 1.3274,
       "step": 75
+    },
+    {
+      "epoch": 0.30522088353413657,
+      "grad_norm": 1.4249285459518433,
+      "learning_rate": 3.308693936411421e-06,
+      "loss": 1.2748,
+      "step": 76
+    },
+    {
+      "epoch": 0.3092369477911647,
+      "grad_norm": 1.1587796211242676,
+      "learning_rate": 3.0534162954100264e-06,
+      "loss": 1.0238,
+      "step": 77
+    },
+    {
+      "epoch": 0.3132530120481928,
+      "grad_norm": 1.302412748336792,
+      "learning_rate": 2.8066019966134907e-06,
+      "loss": 1.3392,
+      "step": 78
+    },
+    {
+      "epoch": 0.3172690763052209,
+      "grad_norm": 1.0670229196548462,
+      "learning_rate": 2.5685517452260566e-06,
+      "loss": 0.8408,
+      "step": 79
+    },
+    {
+      "epoch": 0.321285140562249,
+      "grad_norm": 1.086983561515808,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 0.6949,
+      "step": 80
+    },
+    {
+      "epoch": 0.3253012048192771,
+      "grad_norm": 1.277090311050415,
+      "learning_rate": 2.119892463932781e-06,
+      "loss": 0.8406,
+      "step": 81
+    },
+    {
+      "epoch": 0.3253012048192771,
+      "eval_loss": 0.6291564702987671,
+      "eval_runtime": 32.5821,
+      "eval_samples_per_second": 6.445,
+      "eval_steps_per_second": 0.829,
+      "step": 81
+    },
+    {
+      "epoch": 0.3293172690763052,
+      "grad_norm": 1.555704951286316,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 1.2604,
+      "step": 82
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 1.5652434825897217,
+      "learning_rate": 1.709624274449584e-06,
+      "loss": 1.6627,
+      "step": 83
+    },
+    {
+      "epoch": 0.3373493975903614,
+      "grad_norm": 1.3343106508255005,
+      "learning_rate": 1.5195190384357405e-06,
+      "loss": 1.3886,
+      "step": 84
+    },
+    {
+      "epoch": 0.3413654618473896,
+      "grad_norm": 1.630918264389038,
+      "learning_rate": 1.339745962155613e-06,
+      "loss": 1.4081,
+      "step": 85
+    },
+    {
+      "epoch": 0.3453815261044177,
+      "grad_norm": 1.3480379581451416,
+      "learning_rate": 1.1705240714107301e-06,
+      "loss": 0.8545,
+      "step": 86
+    },
+    {
+      "epoch": 0.3493975903614458,
+      "grad_norm": 1.7904911041259766,
+      "learning_rate": 1.012059537008332e-06,
+      "loss": 1.2855,
+      "step": 87
+    },
+    {
+      "epoch": 0.3534136546184739,
+      "grad_norm": 1.5661286115646362,
+      "learning_rate": 8.645454235739903e-07,
+      "loss": 1.4537,
+      "step": 88
+    },
+    {
+      "epoch": 0.357429718875502,
+      "grad_norm": 1.5383715629577637,
+      "learning_rate": 7.281614543321269e-07,
+      "loss": 1.4315,
+      "step": 89
+    },
+    {
+      "epoch": 0.3614457831325301,
+      "grad_norm": 1.7544879913330078,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 1.5103,
+      "step": 90
+    },
+    {
+      "epoch": 0.3614457831325301,
+      "eval_loss": 0.6263256072998047,
+      "eval_runtime": 32.6143,
+      "eval_samples_per_second": 6.439,
+      "eval_steps_per_second": 0.828,
+      "step": 90
+    },
+    {
+      "epoch": 0.3654618473895582,
+      "grad_norm": 1.6552611589431763,
+      "learning_rate": 4.894348370484648e-07,
+      "loss": 1.7058,
+      "step": 91
+    },
+    {
+      "epoch": 0.36947791164658633,
+      "grad_norm": 1.3507189750671387,
+      "learning_rate": 3.8738304061681107e-07,
+      "loss": 0.9932,
+      "step": 92
+    },
+    {
+      "epoch": 0.37349397590361444,
+      "grad_norm": 1.7394344806671143,
+      "learning_rate": 2.970427372400353e-07,
+      "loss": 1.4815,
+      "step": 93
+    },
+    {
+      "epoch": 0.37751004016064255,
+      "grad_norm": 1.3886154890060425,
+      "learning_rate": 2.1852399266194312e-07,
+      "loss": 0.9411,
+      "step": 94
+    },
+    {
+      "epoch": 0.3815261044176707,
+      "grad_norm": 1.3755466938018799,
+      "learning_rate": 1.519224698779198e-07,
+      "loss": 1.3225,
+      "step": 95
+    },
+    {
+      "epoch": 0.3855421686746988,
+      "grad_norm": 1.3697952032089233,
+      "learning_rate": 9.731931258429638e-08,
+      "loss": 1.307,
+      "step": 96
+    },
+    {
+      "epoch": 0.3895582329317269,
+      "grad_norm": 1.1580904722213745,
+      "learning_rate": 5.4781046317267103e-08,
+      "loss": 0.7828,
+      "step": 97
+    },
+    {
+      "epoch": 0.39357429718875503,
+      "grad_norm": 1.169704794883728,
+      "learning_rate": 2.4359497401758026e-08,
+      "loss": 1.1284,
+      "step": 98
+    },
+    {
+      "epoch": 0.39759036144578314,
+      "grad_norm": 1.4925367832183838,
+      "learning_rate": 6.091729809042379e-09,
+      "loss": 1.0595,
+      "step": 99
+    },
+    {
+      "epoch": 0.39759036144578314,
+      "eval_loss": 0.6255317330360413,
+      "eval_runtime": 32.6,
+      "eval_samples_per_second": 6.442,
+      "eval_steps_per_second": 0.828,
+      "step": 99
+    },
+    {
+      "epoch": 0.40160642570281124,
+      "grad_norm": 1.5164817571640015,
+      "learning_rate": 0.0,
+      "loss": 1.4775,
+      "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": 9.521684545536e+16,
+  "total_flos": 1.2695579394048e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null