Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a383592bf38718fb3cce96c9a37515a13f8e03fe9370d7d2d1a087187a0d133
+oid sha256:710ccb049fdaffaf8fce1380862bdac948ded73a52ed5ed9054c95634fde3e3a
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c93b4db6b7986145d5e6ea61e102bc8f9366b5325396200b7b4f7e71b67f111
+oid sha256:8f171b131291604025ad57072b26d135af815ce58bbb9f25a807601e0e928a7d
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dccf15704fbdf23856e1119baffae48b962f09fb2232cc45a115390986e7d5d
+oid sha256:828a7e6e11ce6fb1a2356180954a5b20df0e28e99bfb6b79a96217eb20a3be28
 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": 0.12106537530266344,
+  "epoch": 0.24213075060532688,
   "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": 3.2021,
       "step": 25
+    },
+    {
+      "epoch": 0.12590799031476999,
+      "grad_norm": 1.662522792816162,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 3.0991,
+      "step": 26
+    },
+    {
+      "epoch": 0.13075060532687652,
+      "grad_norm": 2.686455011367798,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 3.2832,
+      "step": 27
+    },
+    {
+      "epoch": 0.13075060532687652,
+      "eval_loss": 3.157177209854126,
+      "eval_runtime": 18.9382,
+      "eval_samples_per_second": 9.188,
+      "eval_steps_per_second": 1.162,
+      "step": 27
+    },
+    {
+      "epoch": 0.13559322033898305,
+      "grad_norm": 2.5698466300964355,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 3.1181,
+      "step": 28
+    },
+    {
+      "epoch": 0.14043583535108958,
+      "grad_norm": 1.9049105644226074,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 2.9334,
+      "step": 29
+    },
+    {
+      "epoch": 0.14527845036319612,
+      "grad_norm": 2.964027166366577,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 3.2234,
+      "step": 30
+    },
+    {
+      "epoch": 0.15012106537530268,
+      "grad_norm": 1.3506639003753662,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 3.1192,
+      "step": 31
+    },
+    {
+      "epoch": 0.1549636803874092,
+      "grad_norm": 1.3407896757125854,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 3.0793,
+      "step": 32
+    },
+    {
+      "epoch": 0.15980629539951574,
+      "grad_norm": 2.121093988418579,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 3.0593,
+      "step": 33
+    },
+    {
+      "epoch": 0.16464891041162227,
+      "grad_norm": 1.9535635709762573,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 3.2278,
+      "step": 34
+    },
+    {
+      "epoch": 0.1694915254237288,
+      "grad_norm": 2.7124617099761963,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 3.4606,
+      "step": 35
+    },
+    {
+      "epoch": 0.17433414043583534,
+      "grad_norm": 1.7934988737106323,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 3.1656,
+      "step": 36
+    },
+    {
+      "epoch": 0.17433414043583534,
+      "eval_loss": 3.129340171813965,
+      "eval_runtime": 18.9783,
+      "eval_samples_per_second": 9.168,
+      "eval_steps_per_second": 1.159,
+      "step": 36
+    },
+    {
+      "epoch": 0.1791767554479419,
+      "grad_norm": 1.6445538997650146,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 3.0207,
+      "step": 37
+    },
+    {
+      "epoch": 0.18401937046004843,
+      "grad_norm": 1.3065544366836548,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 2.7292,
+      "step": 38
+    },
+    {
+      "epoch": 0.18886198547215496,
+      "grad_norm": 1.4131739139556885,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 2.8626,
+      "step": 39
+    },
+    {
+      "epoch": 0.1937046004842615,
+      "grad_norm": 3.710179328918457,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 3.2187,
+      "step": 40
+    },
+    {
+      "epoch": 0.19854721549636803,
+      "grad_norm": 1.917811393737793,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 3.1257,
+      "step": 41
+    },
+    {
+      "epoch": 0.2033898305084746,
+      "grad_norm": 1.0857932567596436,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 3.0203,
+      "step": 42
+    },
+    {
+      "epoch": 0.20823244552058112,
+      "grad_norm": 0.9913411736488342,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 2.9028,
+      "step": 43
+    },
+    {
+      "epoch": 0.21307506053268765,
+      "grad_norm": 2.206404685974121,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 3.0664,
+      "step": 44
+    },
+    {
+      "epoch": 0.2179176755447942,
+      "grad_norm": 1.5370384454727173,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 2.9419,
+      "step": 45
+    },
+    {
+      "epoch": 0.2179176755447942,
+      "eval_loss": 3.1047704219818115,
+      "eval_runtime": 18.9369,
+      "eval_samples_per_second": 9.188,
+      "eval_steps_per_second": 1.162,
+      "step": 45
+    },
+    {
+      "epoch": 0.22276029055690072,
+      "grad_norm": 1.9688664674758911,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 3.193,
+      "step": 46
+    },
+    {
+      "epoch": 0.22760290556900725,
+      "grad_norm": 2.1754133701324463,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 2.9325,
+      "step": 47
+    },
+    {
+      "epoch": 0.2324455205811138,
+      "grad_norm": 2.6705334186553955,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 3.2207,
+      "step": 48
+    },
+    {
+      "epoch": 0.23728813559322035,
+      "grad_norm": 1.4950735569000244,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 3.0829,
+      "step": 49
+    },
+    {
+      "epoch": 0.24213075060532688,
+      "grad_norm": 2.104860782623291,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 3.1599,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.85471820890112e+16,
+  "total_flos": 3.70943641780224e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null