Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11fd0803d3fc6a5c51ea71901bf1ee016095013eefd2411d6e042f43bc41377c
+oid sha256:34756b4640506f7b5b30d23c6cb5aa75f931315f0037dcde790f81d542e35b03
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1913a0459497214264f8d14cc87a25c0565f3bf6dd57695e3534bb75df7da54
+oid sha256:c916bb85b13044f165616eb5c9bb73afcfbb2ff06b7432c88f8e8a6de1b9d5af
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b3600f4f62c77cfb9f3f36d5a114f6f58022f220d20e149c85171731fd49eb1
+oid sha256:7e13ef812e9e18104cbc17aef37ae8df322b4f01874688fcccab1be3f2f0b3ab
 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": 0.07163323782234957,
+  "epoch": 0.14326647564469913,
   "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": 10.3385,
       "step": 25
+    },
+    {
+      "epoch": 0.07449856733524356,
+      "grad_norm": 0.2284359186887741,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 10.3517,
+      "step": 26
+    },
+    {
+      "epoch": 0.07736389684813753,
+      "grad_norm": 0.22772260010242462,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 10.3457,
+      "step": 27
+    },
+    {
+      "epoch": 0.07736389684813753,
+      "eval_loss": 10.345144271850586,
+      "eval_runtime": 1.0637,
+      "eval_samples_per_second": 276.397,
+      "eval_steps_per_second": 34.785,
+      "step": 27
+    },
+    {
+      "epoch": 0.08022922636103152,
+      "grad_norm": 0.24294577538967133,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 10.3317,
+      "step": 28
+    },
+    {
+      "epoch": 0.0830945558739255,
+      "grad_norm": 0.2539214491844177,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 10.3381,
+      "step": 29
+    },
+    {
+      "epoch": 0.08595988538681948,
+      "grad_norm": 0.20477065443992615,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 10.3582,
+      "step": 30
+    },
+    {
+      "epoch": 0.08882521489971347,
+      "grad_norm": 0.21697883307933807,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 10.3367,
+      "step": 31
+    },
+    {
+      "epoch": 0.09169054441260745,
+      "grad_norm": 0.29203030467033386,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 10.3243,
+      "step": 32
+    },
+    {
+      "epoch": 0.09455587392550144,
+      "grad_norm": 0.23186412453651428,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 10.3584,
+      "step": 33
+    },
+    {
+      "epoch": 0.09742120343839542,
+      "grad_norm": 0.2152336984872818,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 10.3469,
+      "step": 34
+    },
+    {
+      "epoch": 0.10028653295128939,
+      "grad_norm": 0.2645852267742157,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 10.3416,
+      "step": 35
+    },
+    {
+      "epoch": 0.10315186246418338,
+      "grad_norm": 0.19434252381324768,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 10.3436,
+      "step": 36
+    },
+    {
+      "epoch": 0.10315186246418338,
+      "eval_loss": 10.338038444519043,
+      "eval_runtime": 1.0423,
+      "eval_samples_per_second": 282.056,
+      "eval_steps_per_second": 35.497,
+      "step": 36
+    },
+    {
+      "epoch": 0.10601719197707736,
+      "grad_norm": 0.2565288245677948,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 10.3424,
+      "step": 37
+    },
+    {
+      "epoch": 0.10888252148997135,
+      "grad_norm": 0.3266773819923401,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 10.3231,
+      "step": 38
+    },
+    {
+      "epoch": 0.11174785100286533,
+      "grad_norm": 0.30517715215682983,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 10.3282,
+      "step": 39
+    },
+    {
+      "epoch": 0.11461318051575932,
+      "grad_norm": 0.213883176445961,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 10.3301,
+      "step": 40
+    },
+    {
+      "epoch": 0.1174785100286533,
+      "grad_norm": 0.23180383443832397,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 10.337,
+      "step": 41
+    },
+    {
+      "epoch": 0.12034383954154727,
+      "grad_norm": 0.2547537088394165,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 10.3492,
+      "step": 42
+    },
+    {
+      "epoch": 0.12320916905444126,
+      "grad_norm": 0.3248274326324463,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 10.326,
+      "step": 43
+    },
+    {
+      "epoch": 0.12607449856733524,
+      "grad_norm": 0.28297948837280273,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 10.3352,
+      "step": 44
+    },
+    {
+      "epoch": 0.12893982808022922,
+      "grad_norm": 0.2600502371788025,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 10.3567,
+      "step": 45
+    },
+    {
+      "epoch": 0.12893982808022922,
+      "eval_loss": 10.33073902130127,
+      "eval_runtime": 1.0349,
+      "eval_samples_per_second": 284.076,
+      "eval_steps_per_second": 35.751,
+      "step": 45
+    },
+    {
+      "epoch": 0.1318051575931232,
+      "grad_norm": 0.2766321301460266,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 10.3338,
+      "step": 46
+    },
+    {
+      "epoch": 0.1346704871060172,
+      "grad_norm": 0.2638920843601227,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 10.339,
+      "step": 47
+    },
+    {
+      "epoch": 0.13753581661891118,
+      "grad_norm": 0.26153671741485596,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 10.3352,
+      "step": 48
+    },
+    {
+      "epoch": 0.14040114613180515,
+      "grad_norm": 0.27219700813293457,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 10.3293,
+      "step": 49
+    },
+    {
+      "epoch": 0.14326647564469913,
+      "grad_norm": 0.2812553942203522,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 10.3356,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1307561164800.0,
+  "total_flos": 2641273552896.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null