Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fb3e5f6d700f04360cc8d06f85c82571f9b5306a7fe4151a439f9b6ce9fe02b
+oid sha256:9e5a1f2ec1d475492f3059cae40cf7c32deef804b6f63ca30ddf82f00951eee0
 size 432223744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91e7fd517e23a7e78cff7bc0eb64df07e5c4c3c2eca43537242ebda89dca635d
+oid sha256:e35173d0693f827b87b5e8bd0262762b95a04dcc720fa42468f02bab086428bc
 size 864785974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3690c75874142a08d88d20aa2b21b007f34a57f6bf0944b5d03a6c6dd450142f
+oid sha256:a5d43f3578de2b4189ff8d2c0d8ea51645e1b70e7605e6b5d481932800505c7f
 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": 0.005529750055297501,
+  "epoch": 0.011059500110595002,
   "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": 4.849,
       "eval_steps_per_second": 2.424,
       "step": 25
+    },
+    {
+      "epoch": 0.0057509400575094,
+      "grad_norm": 0.936359703540802,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 0.2958,
+      "step": 26
+    },
+    {
+      "epoch": 0.005972130059721301,
+      "grad_norm": 2.5030763149261475,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.4072,
+      "step": 27
+    },
+    {
+      "epoch": 0.0061933200619332,
+      "grad_norm": 1.6899378299713135,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 0.3685,
+      "step": 28
+    },
+    {
+      "epoch": 0.006414510064145101,
+      "grad_norm": 1.4776792526245117,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 0.3621,
+      "step": 29
+    },
+    {
+      "epoch": 0.006635700066357001,
+      "grad_norm": 0.45324471592903137,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.3131,
+      "step": 30
+    },
+    {
+      "epoch": 0.006856890068568901,
+      "grad_norm": 0.3806421160697937,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.3186,
+      "step": 31
+    },
+    {
+      "epoch": 0.007078080070780801,
+      "grad_norm": 0.3761659264564514,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 0.333,
+      "step": 32
+    },
+    {
+      "epoch": 0.0072992700729927005,
+      "grad_norm": 1.2686724662780762,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 0.3683,
+      "step": 33
+    },
+    {
+      "epoch": 0.007520460075204601,
+      "grad_norm": 0.4958406984806061,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 0.3483,
+      "step": 34
+    },
+    {
+      "epoch": 0.0077416500774165,
+      "grad_norm": 0.7048684358596802,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.3599,
+      "step": 35
+    },
+    {
+      "epoch": 0.007962840079628402,
+      "grad_norm": 0.5722953081130981,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 0.318,
+      "step": 36
+    },
+    {
+      "epoch": 0.0081840300818403,
+      "grad_norm": 0.9092257022857666,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 0.3665,
+      "step": 37
+    },
+    {
+      "epoch": 0.0084052200840522,
+      "grad_norm": 0.5776060223579407,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 0.3342,
+      "step": 38
+    },
+    {
+      "epoch": 0.008626410086264101,
+      "grad_norm": 0.20956559479236603,
+      "learning_rate": 5e-05,
+      "loss": 0.3402,
+      "step": 39
+    },
+    {
+      "epoch": 0.008847600088476001,
+      "grad_norm": 0.22896930575370789,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 0.3583,
+      "step": 40
+    },
+    {
+      "epoch": 0.0090687900906879,
+      "grad_norm": 0.27079978585243225,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 0.3455,
+      "step": 41
+    },
+    {
+      "epoch": 0.0092899800928998,
+      "grad_norm": 0.2143234759569168,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.3396,
+      "step": 42
+    },
+    {
+      "epoch": 0.0095111700951117,
+      "grad_norm": 0.4857862889766693,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.3401,
+      "step": 43
+    },
+    {
+      "epoch": 0.009732360097323601,
+      "grad_norm": 0.3611290156841278,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 0.3345,
+      "step": 44
+    },
+    {
+      "epoch": 0.009953550099535502,
+      "grad_norm": 0.481356143951416,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.3469,
+      "step": 45
+    },
+    {
+      "epoch": 0.0101747401017474,
+      "grad_norm": 1.1548091173171997,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 0.4028,
+      "step": 46
+    },
+    {
+      "epoch": 0.0103959301039593,
+      "grad_norm": 0.552361786365509,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.3514,
+      "step": 47
+    },
+    {
+      "epoch": 0.010617120106171201,
+      "grad_norm": 0.2959761321544647,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.3377,
+      "step": 48
+    },
+    {
+      "epoch": 0.010838310108383101,
+      "grad_norm": 0.3817697763442993,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 0.3419,
+      "step": 49
+    },
+    {
+      "epoch": 0.011059500110595002,
+      "grad_norm": 0.612399697303772,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 0.3396,
+      "step": 50
+    },
+    {
+      "epoch": 0.011059500110595002,
+      "eval_loss": 0.32999828457832336,
+      "eval_runtime": 785.7014,
+      "eval_samples_per_second": 4.847,
+      "eval_steps_per_second": 2.423,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.1446136610816e+16,
+  "total_flos": 8.2892273221632e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null