Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cdd8d32fe8db2e7036505ccafee8b112a8cf127d08e0aa20486b07704ae38b6
+oid sha256:8f53abadbe73d719bf92ceebb975e93f99bcaa19acae874c18a0b35430f1b81d
 size 500770656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db337792f3900c3200d5539a00f1a312565617ac5d19d54d2a57d8b30f28ce8b
+oid sha256:83e3262bd01abac8dbd96797ef5d5aac9731cb5120b4cb5395eccc49f4d4370a
 size 1001863522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e04648c773506fe827721155d97cf3bf4c732c1876f34c64b43b79384bacc356
+oid sha256:31fd9039fdc861dba888e5236e84d999e88f526fb2ab44628def9efc8888394f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
+oid sha256:212837ccb433e5430b061dc107b19dc09e932e6cfb62a751187d0903b7b0d94e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01756928888303246,
+  "epoch": 0.02635393332454869,
   "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": 3.9,
       "eval_steps_per_second": 1.951,
       "step": 50
+    },
+    {
+      "epoch": 0.01792067466069311,
+      "grad_norm": 1.2253239154815674,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 5.3973,
+      "step": 51
+    },
+    {
+      "epoch": 0.01827206043835376,
+      "grad_norm": 0.9925060868263245,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 5.1567,
+      "step": 52
+    },
+    {
+      "epoch": 0.018623446216014406,
+      "grad_norm": 1.3718881607055664,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 7.931,
+      "step": 53
+    },
+    {
+      "epoch": 0.018974831993675056,
+      "grad_norm": 1.1585586071014404,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 9.9163,
+      "step": 54
+    },
+    {
+      "epoch": 0.019326217771335707,
+      "grad_norm": 1.292351245880127,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 14.2114,
+      "step": 55
+    },
+    {
+      "epoch": 0.019677603548996354,
+      "grad_norm": 0.7819482088088989,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 5.4162,
+      "step": 56
+    },
+    {
+      "epoch": 0.020028989326657004,
+      "grad_norm": 0.9459342956542969,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 8.4571,
+      "step": 57
+    },
+    {
+      "epoch": 0.020380375104317654,
+      "grad_norm": 0.8447139859199524,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 4.3193,
+      "step": 58
+    },
+    {
+      "epoch": 0.0207317608819783,
+      "grad_norm": 0.9083331823348999,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 5.212,
+      "step": 59
+    },
+    {
+      "epoch": 0.02108314665963895,
+      "grad_norm": 0.9303866028785706,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 5.864,
+      "step": 60
+    },
+    {
+      "epoch": 0.021434532437299602,
+      "grad_norm": 0.9800831079483032,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 5.7093,
+      "step": 61
+    },
+    {
+      "epoch": 0.02178591821496025,
+      "grad_norm": 1.0370510816574097,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 7.2464,
+      "step": 62
+    },
+    {
+      "epoch": 0.0221373039926209,
+      "grad_norm": 1.0886764526367188,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 6.793,
+      "step": 63
+    },
+    {
+      "epoch": 0.02248868977028155,
+      "grad_norm": 1.2717602252960205,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 7.8938,
+      "step": 64
+    },
+    {
+      "epoch": 0.022840075547942196,
+      "grad_norm": 1.13100004196167,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 6.6839,
+      "step": 65
+    },
+    {
+      "epoch": 0.023191461325602847,
+      "grad_norm": 1.103505253791809,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 7.4892,
+      "step": 66
+    },
+    {
+      "epoch": 0.023542847103263497,
+      "grad_norm": 1.0577113628387451,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 6.9858,
+      "step": 67
+    },
+    {
+      "epoch": 0.023894232880924144,
+      "grad_norm": 1.1837400197982788,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 7.707,
+      "step": 68
+    },
+    {
+      "epoch": 0.024245618658584794,
+      "grad_norm": 1.2462010383605957,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 8.0216,
+      "step": 69
+    },
+    {
+      "epoch": 0.02459700443624544,
+      "grad_norm": 1.1442655324935913,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 7.1856,
+      "step": 70
+    },
+    {
+      "epoch": 0.02494839021390609,
+      "grad_norm": 1.1962558031082153,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 7.0156,
+      "step": 71
+    },
+    {
+      "epoch": 0.025299775991566742,
+      "grad_norm": 1.2656418085098267,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 7.6485,
+      "step": 72
+    },
+    {
+      "epoch": 0.02565116176922739,
+      "grad_norm": 1.0747231245040894,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 6.3779,
+      "step": 73
+    },
+    {
+      "epoch": 0.02600254754688804,
+      "grad_norm": 1.213733196258545,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 8.1561,
+      "step": 74
+    },
+    {
+      "epoch": 0.02635393332454869,
+      "grad_norm": 1.571469783782959,
+      "learning_rate": 0.0,
+      "loss": 8.2613,
+      "step": 75
+    },
+    {
+      "epoch": 0.02635393332454869,
+      "eval_loss": 1.00751793384552,
+      "eval_runtime": 614.6938,
+      "eval_samples_per_second": 3.9,
+      "eval_steps_per_second": 1.951,
+      "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": 1.4160475717632e+17,
+  "total_flos": 2.2197502476288e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null