Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e1e1b794744b81650e4843754f6c7c2550071ffccbb7b0dcad7da2b05e8e855
+oid sha256:c9b3fc9dc1625f3fa856dd296645418e0e8044994266992e169e694813db916b
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d64c8b125e5ce3064163a237ab2bd9fad7c0028b38fd58b68f1795525eb03591
+oid sha256:dc92d56e948ad3fc75160ebeafe423d0b6eba53f9dfdb24430d4b326b1c064fd
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d36cf02c5c091e1cf6b7a556033f9afe92924f5c6d18c68aeec7f759f6f16a6c
+oid sha256:40b179568a1cc4fbf3d3fb69d926958affae849b3440fd976101f9b7730bf01c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9d0ac734c8e94d229e85b013b02e79542f9f4417457adf3cb0cf93f80541616
+oid sha256:0b83c49d6e7b3a279e90b74d96eb5e52156a2f094710027e1fc159ded4727533
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05485463521667581,
+  "epoch": 0.10970927043335162,
   "eval_steps": 5,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,221 @@
       "eval_samples_per_second": 8.394,
       "eval_steps_per_second": 4.197,
       "step": 25
+    },
+    {
+      "epoch": 0.05704882062534284,
+      "grad_norm": 1.4059255123138428,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.3548,
+      "step": 26
+    },
+    {
+      "epoch": 0.05924300603400987,
+      "grad_norm": 3.23660945892334,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.5226,
+      "step": 27
+    },
+    {
+      "epoch": 0.061437191442676904,
+      "grad_norm": 9.492186546325684,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 0.4232,
+      "step": 28
+    },
+    {
+      "epoch": 0.06363137685134394,
+      "grad_norm": 1.2060160636901855,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 0.323,
+      "step": 29
+    },
+    {
+      "epoch": 0.06582556226001098,
+      "grad_norm": 3.9120266437530518,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 0.5533,
+      "step": 30
+    },
+    {
+      "epoch": 0.06582556226001098,
+      "eval_loss": 0.5817310810089111,
+      "eval_runtime": 22.8537,
+      "eval_samples_per_second": 8.401,
+      "eval_steps_per_second": 4.201,
+      "step": 30
+    },
+    {
+      "epoch": 0.06801974766867801,
+      "grad_norm": 8.79382038116455,
+      "learning_rate": 5e-05,
+      "loss": 1.0141,
+      "step": 31
+    },
+    {
+      "epoch": 0.07021393307734504,
+      "grad_norm": 7.010884761810303,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 0.4862,
+      "step": 32
+    },
+    {
+      "epoch": 0.07240811848601207,
+      "grad_norm": 10.745322227478027,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 1.0003,
+      "step": 33
+    },
+    {
+      "epoch": 0.0746023038946791,
+      "grad_norm": 3.4400458335876465,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 0.3171,
+      "step": 34
+    },
+    {
+      "epoch": 0.07679648930334614,
+      "grad_norm": 12.523181915283203,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.8103,
+      "step": 35
+    },
+    {
+      "epoch": 0.07679648930334614,
+      "eval_loss": 0.4702953100204468,
+      "eval_runtime": 22.7974,
+      "eval_samples_per_second": 8.422,
+      "eval_steps_per_second": 4.211,
+      "step": 35
+    },
+    {
+      "epoch": 0.07899067471201317,
+      "grad_norm": 10.607621192932129,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.7069,
+      "step": 36
+    },
+    {
+      "epoch": 0.0811848601206802,
+      "grad_norm": 5.708343982696533,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 0.3979,
+      "step": 37
+    },
+    {
+      "epoch": 0.08337904552934723,
+      "grad_norm": 7.0952348709106445,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 0.5199,
+      "step": 38
+    },
+    {
+      "epoch": 0.08557323093801426,
+      "grad_norm": 6.050652980804443,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.4952,
+      "step": 39
+    },
+    {
+      "epoch": 0.0877674163466813,
+      "grad_norm": 3.988201141357422,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 0.4951,
+      "step": 40
+    },
+    {
+      "epoch": 0.0877674163466813,
+      "eval_loss": 0.4913504123687744,
+      "eval_runtime": 22.8247,
+      "eval_samples_per_second": 8.412,
+      "eval_steps_per_second": 4.206,
+      "step": 40
+    },
+    {
+      "epoch": 0.08996160175534833,
+      "grad_norm": 3.5365755558013916,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.4151,
+      "step": 41
+    },
+    {
+      "epoch": 0.09215578716401536,
+      "grad_norm": 2.981470823287964,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 0.3609,
+      "step": 42
+    },
+    {
+      "epoch": 0.09434997257268239,
+      "grad_norm": 7.036005020141602,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.4929,
+      "step": 43
+    },
+    {
+      "epoch": 0.09654415798134942,
+      "grad_norm": 16.351613998413086,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 0.8053,
+      "step": 44
+    },
+    {
+      "epoch": 0.09873834339001646,
+      "grad_norm": 7.42625093460083,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.4763,
+      "step": 45
+    },
+    {
+      "epoch": 0.09873834339001646,
+      "eval_loss": 0.44910240173339844,
+      "eval_runtime": 22.8479,
+      "eval_samples_per_second": 8.403,
+      "eval_steps_per_second": 4.202,
+      "step": 45
+    },
+    {
+      "epoch": 0.10093252879868349,
+      "grad_norm": 6.476613521575928,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4703,
+      "step": 46
+    },
+    {
+      "epoch": 0.10312671420735052,
+      "grad_norm": 6.421245098114014,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.4754,
+      "step": 47
+    },
+    {
+      "epoch": 0.10532089961601755,
+      "grad_norm": 3.1271674633026123,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 0.3527,
+      "step": 48
+    },
+    {
+      "epoch": 0.10751508502468458,
+      "grad_norm": 6.350700855255127,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 0.4567,
+      "step": 49
+    },
+    {
+      "epoch": 0.10970927043335162,
+      "grad_norm": 2.4120147228240967,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 0.3867,
+      "step": 50
+    },
+    {
+      "epoch": 0.10970927043335162,
+      "eval_loss": 0.41695770621299744,
+      "eval_runtime": 22.8514,
+      "eval_samples_per_second": 8.402,
+      "eval_steps_per_second": 4.201,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -244,12 +459,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9273591044505600.0,
+  "total_flos": 1.85471820890112e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null