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:c264c6d2e73732547a7b09f9fc820f657e8fe4ad1afc8c50b41a002e2e044fce
+oid sha256:e62a4cbafe922db7bd8b3df66fdf6beff356b45f3d260e6d6844e0c2e3474e5e
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df14b64bda3cc789624c2c19e230d937bff192a315accd024e513a798059875e
+oid sha256:57e070c5370a3b30c49a481dfe3f4a0eaeb929cd7d12e8c74b05d39512e66013
 size 212298

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:478562ab91048548c00e6717dc344083f63576756137a6709bdd86f5991a0d9f
+oid sha256:8bf1f2e93b143f41946d343a4175e887663c6c6d06dfa2f03f395d77de26be96
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99fc9c0ec571f76cf9b6d1229601c5173899cd18104e487c5627f5f4c56c6e8a
+oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0257201646090535,
+  "epoch": 0.051440329218107,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 210.026,
       "eval_steps_per_second": 105.141,
       "step": 25
+    },
+    {
+      "epoch": 0.026748971193415638,
+      "grad_norm": 0.06006744131445885,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 10.3693,
+      "step": 26
+    },
+    {
+      "epoch": 0.027777777777777776,
+      "grad_norm": 0.061292968690395355,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 10.3781,
+      "step": 27
+    },
+    {
+      "epoch": 0.02880658436213992,
+      "grad_norm": 0.05729150399565697,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 10.3698,
+      "step": 28
+    },
+    {
+      "epoch": 0.029835390946502057,
+      "grad_norm": 0.0738535150885582,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 10.377,
+      "step": 29
+    },
+    {
+      "epoch": 0.030864197530864196,
+      "grad_norm": 0.08201771229505539,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 10.3743,
+      "step": 30
+    },
+    {
+      "epoch": 0.03189300411522634,
+      "grad_norm": 0.06121494248509407,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 10.3732,
+      "step": 31
+    },
+    {
+      "epoch": 0.03292181069958848,
+      "grad_norm": 0.06989278644323349,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 10.3769,
+      "step": 32
+    },
+    {
+      "epoch": 0.033950617283950615,
+      "grad_norm": 0.0654149129986763,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 10.3745,
+      "step": 33
+    },
+    {
+      "epoch": 0.03497942386831276,
+      "grad_norm": 0.07070856541395187,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 10.3761,
+      "step": 34
+    },
+    {
+      "epoch": 0.0360082304526749,
+      "grad_norm": 0.06659887731075287,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 10.3724,
+      "step": 35
+    },
+    {
+      "epoch": 0.037037037037037035,
+      "grad_norm": 0.06675346195697784,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 10.3737,
+      "step": 36
+    },
+    {
+      "epoch": 0.03806584362139918,
+      "grad_norm": 0.07385862618684769,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 10.375,
+      "step": 37
+    },
+    {
+      "epoch": 0.03909465020576132,
+      "grad_norm": 0.07189275324344635,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 10.3731,
+      "step": 38
+    },
+    {
+      "epoch": 0.040123456790123455,
+      "grad_norm": 0.06958039849996567,
+      "learning_rate": 5e-05,
+      "loss": 10.377,
+      "step": 39
+    },
+    {
+      "epoch": 0.0411522633744856,
+      "grad_norm": 0.06426934152841568,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 10.3661,
+      "step": 40
+    },
+    {
+      "epoch": 0.04218106995884774,
+      "grad_norm": 0.05699732154607773,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 10.373,
+      "step": 41
+    },
+    {
+      "epoch": 0.043209876543209874,
+      "grad_norm": 0.07567627727985382,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 10.3706,
+      "step": 42
+    },
+    {
+      "epoch": 0.044238683127572016,
+      "grad_norm": 0.06678629666566849,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 10.3735,
+      "step": 43
+    },
+    {
+      "epoch": 0.04526748971193416,
+      "grad_norm": 0.07194814831018448,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 10.3711,
+      "step": 44
+    },
+    {
+      "epoch": 0.046296296296296294,
+      "grad_norm": 0.07632729411125183,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 10.3723,
+      "step": 45
+    },
+    {
+      "epoch": 0.047325102880658436,
+      "grad_norm": 0.07104772329330444,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 10.3695,
+      "step": 46
+    },
+    {
+      "epoch": 0.04835390946502058,
+      "grad_norm": 0.06831281632184982,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 10.3702,
+      "step": 47
+    },
+    {
+      "epoch": 0.04938271604938271,
+      "grad_norm": 0.06835275888442993,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 10.3736,
+      "step": 48
+    },
+    {
+      "epoch": 0.050411522633744855,
+      "grad_norm": 0.07666638493537903,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 10.3718,
+      "step": 49
+    },
+    {
+      "epoch": 0.051440329218107,
+      "grad_norm": 0.09056751430034637,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 10.3703,
+      "step": 50
+    },
+    {
+      "epoch": 0.051440329218107,
+      "eval_loss": 10.367652893066406,
+      "eval_runtime": 3.8772,
+      "eval_samples_per_second": 211.233,
+      "eval_steps_per_second": 105.745,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2673003724800.0,
+  "total_flos": 5346007449600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null