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:c919c172699fa20d7cb2144b3c8cfeb4f0cee8bed9044e4db05cf251b3613d12
+oid sha256:d3568678d20869f937076f80feb30ec267b475584548f7b3ba485f9fcb66a8c7
 size 550593184

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06cdab77cc497be6751e25b03a204d33768e671f8a68f9c71dc90f7830b4f9f3
+oid sha256:6b265bf48f11d9dddf0e78cdde848536f8df055a66fcd7972a65db3eeaae5277
 size 1101572914

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d27b8c9b9043b626d51c3c18c83b32922be8ca982438d8740e7e4b1c4f056dc
+oid sha256:b9fdee88efd91cfa6340433c2635a8637a32ae79ac7151d1484742aabd142dda
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eda964d5b06109c7ff637060199d72e397eeb7027b50e10972a323edbe81312
+oid sha256:fb0ce41087f0939d63a9a6eb297660d82f62bda022868309a8c97328e5da41a5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0008518903446748335,
+  "epoch": 0.001703780689349667,
   "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": 2.378,
       "eval_steps_per_second": 1.189,
       "step": 25
+    },
+    {
+      "epoch": 0.0008859659584618268,
+      "grad_norm": 3.6202399730682373,
+      "learning_rate": 7.917848237560709e-05,
+      "loss": 0.127,
+      "step": 26
+    },
+    {
+      "epoch": 0.0009200415722488202,
+      "grad_norm": 1.361546516418457,
+      "learning_rate": 7.75e-05,
+      "loss": 0.0881,
+      "step": 27
+    },
+    {
+      "epoch": 0.0009541171860358135,
+      "grad_norm": 3.2597994804382324,
+      "learning_rate": 7.577868759557654e-05,
+      "loss": 0.209,
+      "step": 28
+    },
+    {
+      "epoch": 0.0009881927998228069,
+      "grad_norm": 2.3739514350891113,
+      "learning_rate": 7.401782177833148e-05,
+      "loss": 0.0655,
+      "step": 29
+    },
+    {
+      "epoch": 0.0010222684136098,
+      "grad_norm": 0.39956721663475037,
+      "learning_rate": 7.222075445642904e-05,
+      "loss": 0.013,
+      "step": 30
+    },
+    {
+      "epoch": 0.0010563440273967935,
+      "grad_norm": 2.310549736022949,
+      "learning_rate": 7.03909064496551e-05,
+      "loss": 0.0997,
+      "step": 31
+    },
+    {
+      "epoch": 0.0010904196411837869,
+      "grad_norm": 3.8629372119903564,
+      "learning_rate": 6.853176097769229e-05,
+      "loss": 0.1503,
+      "step": 32
+    },
+    {
+      "epoch": 0.0011244952549707803,
+      "grad_norm": 1.4826256036758423,
+      "learning_rate": 6.664685702961344e-05,
+      "loss": 0.0285,
+      "step": 33
+    },
+    {
+      "epoch": 0.0011585708687577734,
+      "grad_norm": 1.613270878791809,
+      "learning_rate": 6.473978262721463e-05,
+      "loss": 0.0595,
+      "step": 34
+    },
+    {
+      "epoch": 0.0011926464825447668,
+      "grad_norm": 0.6385797262191772,
+      "learning_rate": 6.281416799501188e-05,
+      "loss": 0.0196,
+      "step": 35
+    },
+    {
+      "epoch": 0.0012267220963317602,
+      "grad_norm": 1.283711552619934,
+      "learning_rate": 6.087367864990233e-05,
+      "loss": 0.0276,
+      "step": 36
+    },
+    {
+      "epoch": 0.0012607977101187534,
+      "grad_norm": 5.805143356323242,
+      "learning_rate": 5.8922008423644624e-05,
+      "loss": 0.1078,
+      "step": 37
+    },
+    {
+      "epoch": 0.0012948733239057468,
+      "grad_norm": 0.6078380346298218,
+      "learning_rate": 5.696287243144013e-05,
+      "loss": 0.0143,
+      "step": 38
+    },
+    {
+      "epoch": 0.0013289489376927402,
+      "grad_norm": 1.3938196897506714,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0196,
+      "step": 39
+    },
+    {
+      "epoch": 0.0013630245514797336,
+      "grad_norm": 4.788840293884277,
+      "learning_rate": 5.303712756855988e-05,
+      "loss": 0.1522,
+      "step": 40
+    },
+    {
+      "epoch": 0.0013971001652667268,
+      "grad_norm": 7.833195686340332,
+      "learning_rate": 5.107799157635538e-05,
+      "loss": 0.0832,
+      "step": 41
+    },
+    {
+      "epoch": 0.0014311757790537202,
+      "grad_norm": 6.889073371887207,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.1242,
+      "step": 42
+    },
+    {
+      "epoch": 0.0014652513928407136,
+      "grad_norm": 6.13986349105835,
+      "learning_rate": 4.718583200498814e-05,
+      "loss": 0.0414,
+      "step": 43
+    },
+    {
+      "epoch": 0.0014993270066277068,
+      "grad_norm": 7.624245643615723,
+      "learning_rate": 4.526021737278538e-05,
+      "loss": 0.1478,
+      "step": 44
+    },
+    {
+      "epoch": 0.0015334026204147002,
+      "grad_norm": 0.07408539205789566,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0022,
+      "step": 45
+    },
+    {
+      "epoch": 0.0015674782342016936,
+      "grad_norm": 1.7765361070632935,
+      "learning_rate": 4.146823902230772e-05,
+      "loss": 0.1055,
+      "step": 46
+    },
+    {
+      "epoch": 0.001601553847988687,
+      "grad_norm": 1.6538923978805542,
+      "learning_rate": 3.960909355034491e-05,
+      "loss": 0.0226,
+      "step": 47
+    },
+    {
+      "epoch": 0.0016356294617756802,
+      "grad_norm": 13.931591987609863,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.2841,
+      "step": 48
+    },
+    {
+      "epoch": 0.0016697050755626736,
+      "grad_norm": 11.1533203125,
+      "learning_rate": 3.598217822166854e-05,
+      "loss": 0.1394,
+      "step": 49
+    },
+    {
+      "epoch": 0.001703780689349667,
+      "grad_norm": 4.493430137634277,
+      "learning_rate": 3.422131240442349e-05,
+      "loss": 0.0744,
+      "step": 50
+    },
+    {
+      "epoch": 0.001703780689349667,
+      "eval_loss": 0.0442812517285347,
+      "eval_runtime": 5199.0583,
+      "eval_samples_per_second": 2.377,
+      "eval_steps_per_second": 1.188,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.014178406321357e+16,
+  "total_flos": 1.3958909501689037e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null