Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:626c396850af2765e152700b776e8c6b84ea992a0b23a7e023b5b83d69cca321
+oid sha256:4b133a3bf2757652aeca09aaeea47de550b8c846f5e312cf0bcd687b111b06ab
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:460c8b3c4770f25987d801dfbab0fa9a8eab15cd2ab87fdea88200e85b89a2c5
+oid sha256:dc58ee1a7fe380fa37d2351d8ae1203828d56fbc1e860a6eeb282362652b0eea
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48b571a1cda1c18e0b76f3cd6c89bae53eb9d1241ef187c71a1c58bcd4925246
+oid sha256:bf7884caf161c2ce1c9ec67b264a8b146600888d6f011a86ff7659e220ad4974
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d914dc409ae93ac75985631a9974025ebaa397f621307eef226e7d6e1076a1f6
+oid sha256:babd43118aa66a4f5266d730539cf7f09611158b169d9e63dbcb83f6bbaa8626
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.018642803877703208,
+  "epoch": 0.02796420581655481,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 4.414,
       "eval_steps_per_second": 2.208,
       "step": 50
+    },
+    {
+      "epoch": 0.01901565995525727,
+      "grad_norm": 9.196285247802734,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.7973,
+      "step": 51
+    },
+    {
+      "epoch": 0.019388516032811335,
+      "grad_norm": 6.420137882232666,
+      "learning_rate": 4.6270039165317605e-05,
+      "loss": 1.7155,
+      "step": 52
+    },
+    {
+      "epoch": 0.0197613721103654,
+      "grad_norm": 6.166407585144043,
+      "learning_rate": 4.264235636489542e-05,
+      "loss": 1.1948,
+      "step": 53
+    },
+    {
+      "epoch": 0.020134228187919462,
+      "grad_norm": 7.9364776611328125,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 2.2336,
+      "step": 54
+    },
+    {
+      "epoch": 0.020507084265473527,
+      "grad_norm": 6.744062900543213,
+      "learning_rate": 3.5721239031346066e-05,
+      "loss": 2.0732,
+      "step": 55
+    },
+    {
+      "epoch": 0.020879940343027592,
+      "grad_norm": 6.412101745605469,
+      "learning_rate": 3.244097923843398e-05,
+      "loss": 2.3604,
+      "step": 56
+    },
+    {
+      "epoch": 0.021252796420581657,
+      "grad_norm": 7.558949947357178,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 1.5866,
+      "step": 57
+    },
+    {
+      "epoch": 0.02162565249813572,
+      "grad_norm": 5.778247356414795,
+      "learning_rate": 2.6272266318987603e-05,
+      "loss": 2.12,
+      "step": 58
+    },
+    {
+      "epoch": 0.021998508575689784,
+      "grad_norm": 9.419931411743164,
+      "learning_rate": 2.339555568810221e-05,
+      "loss": 2.0553,
+      "step": 59
+    },
+    {
+      "epoch": 0.02237136465324385,
+      "grad_norm": 7.691293716430664,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 2.2256,
+      "step": 60
+    },
+    {
+      "epoch": 0.02274422073079791,
+      "grad_norm": 6.940426826477051,
+      "learning_rate": 1.808479557110081e-05,
+      "loss": 2.3064,
+      "step": 61
+    },
+    {
+      "epoch": 0.023117076808351976,
+      "grad_norm": 8.362802505493164,
+      "learning_rate": 1.566085541871145e-05,
+      "loss": 2.308,
+      "step": 62
+    },
+    {
+      "epoch": 0.02348993288590604,
+      "grad_norm": 6.858037948608398,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 1.7986,
+      "step": 63
+    },
+    {
+      "epoch": 0.023862788963460103,
+      "grad_norm": 8.502093315124512,
+      "learning_rate": 1.129891668217783e-05,
+      "loss": 2.4218,
+      "step": 64
+    },
+    {
+      "epoch": 0.024235645041014168,
+      "grad_norm": 4.750255584716797,
+      "learning_rate": 9.369221296335006e-06,
+      "loss": 1.1287,
+      "step": 65
+    },
+    {
+      "epoch": 0.024608501118568233,
+      "grad_norm": 6.325159072875977,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 1.961,
+      "step": 66
+    },
+    {
+      "epoch": 0.024981357196122298,
+      "grad_norm": 5.899595737457275,
+      "learning_rate": 6.030737921409169e-06,
+      "loss": 1.5426,
+      "step": 67
+    },
+    {
+      "epoch": 0.02535421327367636,
+      "grad_norm": 9.170677185058594,
+      "learning_rate": 4.628304925177318e-06,
+      "loss": 2.2986,
+      "step": 68
+    },
+    {
+      "epoch": 0.025727069351230425,
+      "grad_norm": 11.1466646194458,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 1.9698,
+      "step": 69
+    },
+    {
+      "epoch": 0.02609992542878449,
+      "grad_norm": 5.2693190574646,
+      "learning_rate": 2.3703992880066638e-06,
+      "loss": 1.1575,
+      "step": 70
+    },
+    {
+      "epoch": 0.02647278150633855,
+      "grad_norm": 17.38636016845703,
+      "learning_rate": 1.5192246987791981e-06,
+      "loss": 2.5558,
+      "step": 71
+    },
+    {
+      "epoch": 0.026845637583892617,
+      "grad_norm": 7.246407985687256,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 2.2891,
+      "step": 72
+    },
+    {
+      "epoch": 0.027218493661446682,
+      "grad_norm": 11.300233840942383,
+      "learning_rate": 3.805301908254455e-07,
+      "loss": 2.0134,
+      "step": 73
+    },
+    {
+      "epoch": 0.027591349739000747,
+      "grad_norm": 7.813751220703125,
+      "learning_rate": 9.517784181422019e-08,
+      "loss": 2.4345,
+      "step": 74
+    },
+    {
+      "epoch": 0.02796420581655481,
+      "grad_norm": 9.342615127563477,
+      "learning_rate": 0.0,
+      "loss": 1.7863,
+      "step": 75
+    },
+    {
+      "epoch": 0.02796420581655481,
+      "eval_loss": 0.2411356121301651,
+      "eval_runtime": 511.7025,
+      "eval_samples_per_second": 4.415,
+      "eval_steps_per_second": 2.208,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -395,12 +578,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.2695579394048e+17,
+  "total_flos": 1.9043369091072e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null