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:eabe2453282680710f400f28dd8c092a89f6f699486a311f878fca120bad2e57
+oid sha256:bb0e929713b030d6427f4894036191e886f42fd5cfd2f14e142d7b9be7ba94fc
 size 767856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d50070ec98c1b73bca145cf4ff1892fd1b8080bca66dcd8a266cd85499ba6e87
+oid sha256:aa03ee44f98d935368a41ca7286fca9416a8a3d2d751cc8f6b9117913bf90d15
 size 1601338

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33edfe694fa165baa61532acb2b10479613e785ceb88d728c000b29743b6ba96
+oid sha256:9d2cd6e017a2b7c4b64b80508be5faa91cd43d9e5da242365e5dd929349474a0
 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": 0.001236781893513079,
+  "epoch": 0.002473563787026158,
   "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": 89.611,
       "eval_steps_per_second": 44.811,
       "step": 25
+    },
+    {
+      "epoch": 0.001286253169253602,
+      "grad_norm": 5.88217830657959,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 7.0338,
+      "step": 26
+    },
+    {
+      "epoch": 0.0013357244449941253,
+      "grad_norm": 5.846419811248779,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 7.1329,
+      "step": 27
+    },
+    {
+      "epoch": 0.0013851957207346485,
+      "grad_norm": 5.849457740783691,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 6.7678,
+      "step": 28
+    },
+    {
+      "epoch": 0.0014346669964751715,
+      "grad_norm": 5.783066749572754,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 6.8641,
+      "step": 29
+    },
+    {
+      "epoch": 0.0014841382722156947,
+      "grad_norm": 5.95844030380249,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 6.7875,
+      "step": 30
+    },
+    {
+      "epoch": 0.0014841382722156947,
+      "eval_loss": 6.735217094421387,
+      "eval_runtime": 95.4239,
+      "eval_samples_per_second": 89.192,
+      "eval_steps_per_second": 44.601,
+      "step": 30
+    },
+    {
+      "epoch": 0.001533609547956218,
+      "grad_norm": 5.942857265472412,
+      "learning_rate": 5e-05,
+      "loss": 6.7855,
+      "step": 31
+    },
+    {
+      "epoch": 0.0015830808236967412,
+      "grad_norm": 5.439502716064453,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 6.6782,
+      "step": 32
+    },
+    {
+      "epoch": 0.0016325520994372642,
+      "grad_norm": 5.478299617767334,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 6.6382,
+      "step": 33
+    },
+    {
+      "epoch": 0.0016820233751777874,
+      "grad_norm": 6.273443698883057,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 6.5828,
+      "step": 34
+    },
+    {
+      "epoch": 0.0017314946509183107,
+      "grad_norm": 6.156881332397461,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 6.6771,
+      "step": 35
+    },
+    {
+      "epoch": 0.0017314946509183107,
+      "eval_loss": 6.5112690925598145,
+      "eval_runtime": 95.7427,
+      "eval_samples_per_second": 88.895,
+      "eval_steps_per_second": 44.452,
+      "step": 35
+    },
+    {
+      "epoch": 0.0017809659266588337,
+      "grad_norm": 5.457279205322266,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 6.563,
+      "step": 36
+    },
+    {
+      "epoch": 0.001830437202399357,
+      "grad_norm": 5.992366790771484,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 6.4556,
+      "step": 37
+    },
+    {
+      "epoch": 0.0018799084781398801,
+      "grad_norm": 6.0998029708862305,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 6.4219,
+      "step": 38
+    },
+    {
+      "epoch": 0.0019293797538804031,
+      "grad_norm": 5.670993328094482,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 6.4434,
+      "step": 39
+    },
+    {
+      "epoch": 0.001978851029620926,
+      "grad_norm": 5.718242168426514,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 6.4194,
+      "step": 40
+    },
+    {
+      "epoch": 0.001978851029620926,
+      "eval_loss": 6.370116233825684,
+      "eval_runtime": 95.6,
+      "eval_samples_per_second": 89.027,
+      "eval_steps_per_second": 44.519,
+      "step": 40
+    },
+    {
+      "epoch": 0.0020283223053614496,
+      "grad_norm": 5.832897663116455,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 6.417,
+      "step": 41
+    },
+    {
+      "epoch": 0.0020777935811019726,
+      "grad_norm": 5.707322120666504,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 6.3907,
+      "step": 42
+    },
+    {
+      "epoch": 0.0021272648568424956,
+      "grad_norm": 6.1590800285339355,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 6.3305,
+      "step": 43
+    },
+    {
+      "epoch": 0.002176736132583019,
+      "grad_norm": 5.986573696136475,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 6.4059,
+      "step": 44
+    },
+    {
+      "epoch": 0.002226207408323542,
+      "grad_norm": 5.721052169799805,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 6.3249,
+      "step": 45
+    },
+    {
+      "epoch": 0.002226207408323542,
+      "eval_loss": 6.304693698883057,
+      "eval_runtime": 94.88,
+      "eval_samples_per_second": 89.703,
+      "eval_steps_per_second": 44.857,
+      "step": 45
+    },
+    {
+      "epoch": 0.002275678684064065,
+      "grad_norm": 6.428943634033203,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 6.2422,
+      "step": 46
+    },
+    {
+      "epoch": 0.0023251499598045886,
+      "grad_norm": 5.835705280303955,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 6.2458,
+      "step": 47
+    },
+    {
+      "epoch": 0.0023746212355451116,
+      "grad_norm": 6.010042667388916,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 6.4163,
+      "step": 48
+    },
+    {
+      "epoch": 0.0024240925112856346,
+      "grad_norm": 5.472652912139893,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 6.2867,
+      "step": 49
+    },
+    {
+      "epoch": 0.002473563787026158,
+      "grad_norm": 5.85940408706665,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 6.1921,
+      "step": 50
+    },
+    {
+      "epoch": 0.002473563787026158,
+      "eval_loss": 6.28983211517334,
+      "eval_runtime": 94.9476,
+      "eval_samples_per_second": 89.639,
+      "eval_steps_per_second": 44.825,
+      "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": 3393690009600.0,
+  "total_flos": 6787380019200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null