Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f22f628d86409bcc75e72bfafdfad788b2c1e723a52d244add5af0c3237ba7d
+oid sha256:b40974ca04771d61afb89c96407fbb4c5244e89c42d8283a1578ad64c593ee39
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f61f4c96617843e2df8b1763e4da9486a3ced6a741282e511970b389d6ea24e1
+oid sha256:50f9d259f5c438da1f9e66d5dea44e419da0e4fe5acfe2de956c0a2ff418445d
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:407d3bc893aa8f576a0dfe46d188aae89c365711d3d2ee6ac1dd8620cd7e4875
+oid sha256:746265868ea39879f535fee056f526b65cfa4879f40f6a4f2d60e9e7c780bf22
 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": 0.0071256791662955375,
+  "epoch": 0.010688518749443307,
   "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": 8.914,
       "eval_steps_per_second": 4.458,
       "step": 50
+    },
+    {
+      "epoch": 0.007268192749621448,
+      "grad_norm": 0.406108558177948,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.4125,
+      "step": 51
+    },
+    {
+      "epoch": 0.007410706332947359,
+      "grad_norm": 0.46124741435050964,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 0.2856,
+      "step": 52
+    },
+    {
+      "epoch": 0.00755321991627327,
+      "grad_norm": 0.5175564289093018,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 0.3434,
+      "step": 53
+    },
+    {
+      "epoch": 0.00769573349959918,
+      "grad_norm": 0.4141230583190918,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.2163,
+      "step": 54
+    },
+    {
+      "epoch": 0.007838247082925092,
+      "grad_norm": 0.5257975459098816,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.3133,
+      "step": 55
+    },
+    {
+      "epoch": 0.007980760666251002,
+      "grad_norm": 0.480843722820282,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 0.2629,
+      "step": 56
+    },
+    {
+      "epoch": 0.008123274249576913,
+      "grad_norm": 0.5092347860336304,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.3373,
+      "step": 57
+    },
+    {
+      "epoch": 0.008265787832902823,
+      "grad_norm": 0.6335684061050415,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 0.2306,
+      "step": 58
+    },
+    {
+      "epoch": 0.008408301416228734,
+      "grad_norm": 0.4471769630908966,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.2458,
+      "step": 59
+    },
+    {
+      "epoch": 0.008550814999554644,
+      "grad_norm": 0.5540795922279358,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.3237,
+      "step": 60
+    },
+    {
+      "epoch": 0.008693328582880556,
+      "grad_norm": 0.563100278377533,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 0.289,
+      "step": 61
+    },
+    {
+      "epoch": 0.008835842166206467,
+      "grad_norm": 0.7537733912467957,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 0.234,
+      "step": 62
+    },
+    {
+      "epoch": 0.008978355749532377,
+      "grad_norm": 0.5941769480705261,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.3997,
+      "step": 63
+    },
+    {
+      "epoch": 0.009120869332858288,
+      "grad_norm": 0.4771871864795685,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 0.2874,
+      "step": 64
+    },
+    {
+      "epoch": 0.009263382916184199,
+      "grad_norm": 0.5075575113296509,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 0.2415,
+      "step": 65
+    },
+    {
+      "epoch": 0.009405896499510109,
+      "grad_norm": 0.5450537204742432,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.271,
+      "step": 66
+    },
+    {
+      "epoch": 0.00954841008283602,
+      "grad_norm": 0.5052174925804138,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.2612,
+      "step": 67
+    },
+    {
+      "epoch": 0.009690923666161932,
+      "grad_norm": 0.38948696851730347,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 0.2249,
+      "step": 68
+    },
+    {
+      "epoch": 0.009833437249487842,
+      "grad_norm": 0.44858595728874207,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.2774,
+      "step": 69
+    },
+    {
+      "epoch": 0.009975950832813753,
+      "grad_norm": 0.4744488596916199,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 0.3045,
+      "step": 70
+    },
+    {
+      "epoch": 0.010118464416139663,
+      "grad_norm": 0.5326921343803406,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.2987,
+      "step": 71
+    },
+    {
+      "epoch": 0.010260977999465574,
+      "grad_norm": 0.5433304905891418,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.3229,
+      "step": 72
+    },
+    {
+      "epoch": 0.010403491582791484,
+      "grad_norm": 0.5645239353179932,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 0.2353,
+      "step": 73
+    },
+    {
+      "epoch": 0.010546005166117395,
+      "grad_norm": 0.4569799602031708,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 0.2181,
+      "step": 74
+    },
+    {
+      "epoch": 0.010688518749443307,
+      "grad_norm": 0.4840969145298004,
+      "learning_rate": 0.0,
+      "loss": 0.2345,
+      "step": 75
+    },
+    {
+      "epoch": 0.010688518749443307,
+      "eval_loss": 0.22989000380039215,
+      "eval_runtime": 661.6996,
+      "eval_samples_per_second": 8.93,
+      "eval_steps_per_second": 4.466,
+      "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": 7.478754782950195e+16,
+  "total_flos": 1.1208807043773235e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null