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:dd2187c34310b698b72a1fd5897f0ec2f6151d7c3cdd45e3af237182ea580bd8
+oid sha256:4179ef2296562e52cce9db137c9b2c7fe45e23371b4eab3b1d940f8236f41a9e
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d5554d4ebb13188acc94d45637e87c8cfd672eedb3cb6b025d18bae12ef58bb
+oid sha256:1ee61926f886a738682978343fecbd9486d35ab24377301ffa8ea46a06868a10
 size 118090

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccd5f96a0c54d9c7fc696cd2de657ab87643082dd5b551287b669ca224896764
+oid sha256:68d8240f8b64502e023794a3da2d8c6aa526ac0f753e37b389fdd87097fabd55
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b163f39dfe27dc2b3dbffe608a672c5c24782a59c01d78ba19fb42e537b1c880
+oid sha256:f117663bca47e6dbbfa0c77eb3eb3ed1ed85a3dd0c9f866227e737a73eb5c422
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3c2e9f653665898599ba92c14fead2834af70cd76abf31d5deed9f0b6254a84
+oid sha256:7a7d87a0b1f18c774b632725605bde69fd2b07215dcf9ac48e19e6caa47a6c61
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b04fb1bf3df1d2f6147ab7478673cead0a366e5db2e2dbeb350bb77196eaef95
+oid sha256:f3daeca24213bd8e7f686bd89b9bb6ba8b6995471fd68b15febf485beb753100
 size 15024

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": 0.01086484137331595,
+  "epoch": 0.0217296827466319,
   "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": 10.3524,
       "step": 25
+    },
+    {
+      "epoch": 0.011299435028248588,
+      "grad_norm": 1.6594668626785278,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 10.3408,
+      "step": 26
+    },
+    {
+      "epoch": 0.011734028683181226,
+      "grad_norm": 1.6574015617370605,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 10.3433,
+      "step": 27
+    },
+    {
+      "epoch": 0.011734028683181226,
+      "eval_loss": 10.332037925720215,
+      "eval_runtime": 4.4025,
+      "eval_samples_per_second": 1760.591,
+      "eval_steps_per_second": 55.196,
+      "step": 27
+    },
+    {
+      "epoch": 0.012168622338113864,
+      "grad_norm": 1.6417022943496704,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 10.3352,
+      "step": 28
+    },
+    {
+      "epoch": 0.012603215993046502,
+      "grad_norm": 1.6392464637756348,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 10.3281,
+      "step": 29
+    },
+    {
+      "epoch": 0.01303780964797914,
+      "grad_norm": 1.6714566946029663,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 10.3287,
+      "step": 30
+    },
+    {
+      "epoch": 0.013472403302911778,
+      "grad_norm": 1.6938108205795288,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 10.3242,
+      "step": 31
+    },
+    {
+      "epoch": 0.013906996957844416,
+      "grad_norm": 1.8171216249465942,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 10.311,
+      "step": 32
+    },
+    {
+      "epoch": 0.014341590612777053,
+      "grad_norm": 1.7566795349121094,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 10.3095,
+      "step": 33
+    },
+    {
+      "epoch": 0.01477618426770969,
+      "grad_norm": 1.7736107110977173,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 10.2989,
+      "step": 34
+    },
+    {
+      "epoch": 0.015210777922642329,
+      "grad_norm": 1.776149034500122,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 10.3029,
+      "step": 35
+    },
+    {
+      "epoch": 0.01564537157757497,
+      "grad_norm": 1.7460124492645264,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 10.3025,
+      "step": 36
+    },
+    {
+      "epoch": 0.01564537157757497,
+      "eval_loss": 10.295435905456543,
+      "eval_runtime": 4.3752,
+      "eval_samples_per_second": 1771.593,
+      "eval_steps_per_second": 55.541,
+      "step": 36
+    },
+    {
+      "epoch": 0.016079965232507605,
+      "grad_norm": 1.8232313394546509,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 10.2951,
+      "step": 37
+    },
+    {
+      "epoch": 0.016514558887440245,
+      "grad_norm": 1.7527620792388916,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 10.2857,
+      "step": 38
+    },
+    {
+      "epoch": 0.01694915254237288,
+      "grad_norm": 1.7404676675796509,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 10.2875,
+      "step": 39
+    },
+    {
+      "epoch": 0.017383746197305518,
+      "grad_norm": 1.8285305500030518,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 10.2828,
+      "step": 40
+    },
+    {
+      "epoch": 0.017818339852238158,
+      "grad_norm": 1.7420995235443115,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 10.2849,
+      "step": 41
+    },
+    {
+      "epoch": 0.018252933507170794,
+      "grad_norm": 1.7493330240249634,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 10.2871,
+      "step": 42
+    },
+    {
+      "epoch": 0.018687527162103434,
+      "grad_norm": 1.7411251068115234,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 10.2775,
+      "step": 43
+    },
+    {
+      "epoch": 0.01912212081703607,
+      "grad_norm": 1.7749557495117188,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 10.2578,
+      "step": 44
+    },
+    {
+      "epoch": 0.01955671447196871,
+      "grad_norm": 1.7583379745483398,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 10.2678,
+      "step": 45
+    },
+    {
+      "epoch": 0.01955671447196871,
+      "eval_loss": 10.261744499206543,
+      "eval_runtime": 4.3669,
+      "eval_samples_per_second": 1774.935,
+      "eval_steps_per_second": 55.646,
+      "step": 45
+    },
+    {
+      "epoch": 0.019991308126901346,
+      "grad_norm": 1.7365025281906128,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 10.2571,
+      "step": 46
+    },
+    {
+      "epoch": 0.020425901781833986,
+      "grad_norm": 1.7217011451721191,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 10.2583,
+      "step": 47
+    },
+    {
+      "epoch": 0.020860495436766623,
+      "grad_norm": 1.7320549488067627,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 10.2667,
+      "step": 48
+    },
+    {
+      "epoch": 0.021295089091699262,
+      "grad_norm": 1.7598958015441895,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 10.2522,
+      "step": 49
+    },
+    {
+      "epoch": 0.0217296827466319,
+      "grad_norm": 1.7420951128005981,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 10.2627,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5230244659200.0,
+  "total_flos": 10460489318400.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null