Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b10960107e3520b2d4876a55eed6ab2b6837d510f2019c737f899fd77760333
+oid sha256:df9675b8b429fce62e6ff8894dc2719b406d92def43d2f5f750481a9e2154aa7
 size 767856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2cfde06ea4acdbbff47378cf44e495a4d4e720307a975d96cc7cc36e91657df
+oid sha256:03cc383ddbb970086c33a92448b79eeee8dbf43723473d712f50eac130f9d91c
 size 1601338

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dd3658f6815e6bcb8b59c0a60606c053357685d6b00ff6b1a73f72a67169a37
+oid sha256:561c96a9de2039e2fc252d4f61038d8c0e79bafac8eb8ddb35ced95407e0d204
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c931ece4da598a541d357f6c98f67481603252e193960022d37ddd49c584b1f
+oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004500450045004501,
+  "epoch": 0.009000900090009001,
   "eval_steps": 9,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -206,6 +206,205 @@
       "learning_rate": 9.330127018922194e-05,
       "loss": 10.7997,
       "step": 25
+    },
+    {
+      "epoch": 0.00468046804680468,
+      "grad_norm": 5.896301746368408,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 10.8154,
+      "step": 26
+    },
+    {
+      "epoch": 0.00486048604860486,
+      "grad_norm": 6.108735084533691,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 10.477,
+      "step": 27
+    },
+    {
+      "epoch": 0.00486048604860486,
+      "eval_loss": 10.479217529296875,
+      "eval_runtime": 41.5514,
+      "eval_samples_per_second": 112.583,
+      "eval_steps_per_second": 14.079,
+      "step": 27
+    },
+    {
+      "epoch": 0.005040504050405041,
+      "grad_norm": 6.187192916870117,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 10.7532,
+      "step": 28
+    },
+    {
+      "epoch": 0.00522052205220522,
+      "grad_norm": 6.162825107574463,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 10.0425,
+      "step": 29
+    },
+    {
+      "epoch": 0.0054005400540054005,
+      "grad_norm": 5.06771993637085,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 10.6456,
+      "step": 30
+    },
+    {
+      "epoch": 0.005580558055805581,
+      "grad_norm": 6.633289813995361,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 10.5557,
+      "step": 31
+    },
+    {
+      "epoch": 0.00576057605760576,
+      "grad_norm": 7.135171413421631,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 10.4076,
+      "step": 32
+    },
+    {
+      "epoch": 0.005940594059405941,
+      "grad_norm": 6.247159481048584,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 10.2683,
+      "step": 33
+    },
+    {
+      "epoch": 0.006120612061206121,
+      "grad_norm": 5.888491153717041,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 10.3905,
+      "step": 34
+    },
+    {
+      "epoch": 0.0063006300630063005,
+      "grad_norm": 6.2340407371521,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 10.0002,
+      "step": 35
+    },
+    {
+      "epoch": 0.006480648064806481,
+      "grad_norm": 5.402869701385498,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 10.0471,
+      "step": 36
+    },
+    {
+      "epoch": 0.006480648064806481,
+      "eval_loss": 10.007487297058105,
+      "eval_runtime": 41.5019,
+      "eval_samples_per_second": 112.718,
+      "eval_steps_per_second": 14.096,
+      "step": 36
+    },
+    {
+      "epoch": 0.00666066606660666,
+      "grad_norm": 6.251911163330078,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 10.0034,
+      "step": 37
+    },
+    {
+      "epoch": 0.006840684068406841,
+      "grad_norm": 7.18772554397583,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 10.0799,
+      "step": 38
+    },
+    {
+      "epoch": 0.007020702070207021,
+      "grad_norm": 6.769697666168213,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 9.8849,
+      "step": 39
+    },
+    {
+      "epoch": 0.0072007200720072,
+      "grad_norm": 6.6725568771362305,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 10.18,
+      "step": 40
+    },
+    {
+      "epoch": 0.007380738073807381,
+      "grad_norm": 7.166985511779785,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 9.7688,
+      "step": 41
+    },
+    {
+      "epoch": 0.007560756075607561,
+      "grad_norm": 5.779541015625,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 9.6471,
+      "step": 42
+    },
+    {
+      "epoch": 0.0077407740774077406,
+      "grad_norm": 7.53178596496582,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 9.5978,
+      "step": 43
+    },
+    {
+      "epoch": 0.007920792079207921,
+      "grad_norm": 5.810229301452637,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 9.6907,
+      "step": 44
+    },
+    {
+      "epoch": 0.008100810081008101,
+      "grad_norm": 5.271368980407715,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 9.7006,
+      "step": 45
+    },
+    {
+      "epoch": 0.008100810081008101,
+      "eval_loss": 9.594242095947266,
+      "eval_runtime": 41.4612,
+      "eval_samples_per_second": 112.828,
+      "eval_steps_per_second": 14.11,
+      "step": 45
+    },
+    {
+      "epoch": 0.008280828082808282,
+      "grad_norm": 6.034334182739258,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 9.9457,
+      "step": 46
+    },
+    {
+      "epoch": 0.00846084608460846,
+      "grad_norm": 6.873132228851318,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 9.3553,
+      "step": 47
+    },
+    {
+      "epoch": 0.00864086408640864,
+      "grad_norm": 5.189530849456787,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 9.7457,
+      "step": 48
+    },
+    {
+      "epoch": 0.00882088208820882,
+      "grad_norm": 4.753223896026611,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 9.5327,
+      "step": 49
+    },
+    {
+      "epoch": 0.009000900090009001,
+      "grad_norm": 5.407626628875732,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 9.4796,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6787380019200.0,
+  "total_flos": 13574760038400.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null