Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89b6425fc6e5f3cd8e274e5c0eef41d1c89d5694aeecbbed521cbcc7d1342c24
+oid sha256:bc6be646f75e52d433d1eaa9ab9fb47a06ab36db6d03b331a64a36d223bb9a00
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3623ca08a34d444dd74e80c13da02de0f4fc0f4968aeb3dd85deebe07dd3e0c0
+oid sha256:c3b3e536f2055e9bb35676d2b4d438fc49edd6e466f6341bbdb2f5d4fcd405e5
 size 90365754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:026030288cd601691b26a9dd3addc963d8372e0cdb3ae5ae397bb1e558a3e4d2
+oid sha256:a4a797e4556a00e672702ff04c6ecce740fabaca58e7ff5b6ddf14351f843364
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d8615f1aeccd0f9873fc0cf2c0322fde20ac202421c015654a471730a5fa755
+oid sha256:feed204db996a9f7ac3167cc4686c04dccd6605b9b2a7d539da6ff57c605983d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.17667844522968199,
+  "epoch": 0.26501766784452296,
   "eval_steps": 9,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -405,6 +405,205 @@
       "learning_rate": 1.1736481776669307e-05,
       "loss": 3.2573,
       "step": 50
+    },
+    {
+      "epoch": 0.18021201413427562,
+      "grad_norm": 3.6461217403411865,
+      "learning_rate": 1.1391731009600655e-05,
+      "loss": 3.2947,
+      "step": 51
+    },
+    {
+      "epoch": 0.18374558303886926,
+      "grad_norm": 3.643479347229004,
+      "learning_rate": 1.1045284632676535e-05,
+      "loss": 3.2125,
+      "step": 52
+    },
+    {
+      "epoch": 0.1872791519434629,
+      "grad_norm": 3.4164750576019287,
+      "learning_rate": 1.0697564737441254e-05,
+      "loss": 3.3438,
+      "step": 53
+    },
+    {
+      "epoch": 0.19081272084805653,
+      "grad_norm": 3.781705856323242,
+      "learning_rate": 1.0348994967025012e-05,
+      "loss": 3.251,
+      "step": 54
+    },
+    {
+      "epoch": 0.19081272084805653,
+      "eval_loss": 3.2505455017089844,
+      "eval_runtime": 7.1694,
+      "eval_samples_per_second": 33.336,
+      "eval_steps_per_second": 4.184,
+      "step": 54
+    },
+    {
+      "epoch": 0.19434628975265017,
+      "grad_norm": 3.5788426399230957,
+      "learning_rate": 1e-05,
+      "loss": 3.3719,
+      "step": 55
+    },
+    {
+      "epoch": 0.1978798586572438,
+      "grad_norm": 3.601278305053711,
+      "learning_rate": 9.651005032974994e-06,
+      "loss": 3.2865,
+      "step": 56
+    },
+    {
+      "epoch": 0.20141342756183744,
+      "grad_norm": 3.5564422607421875,
+      "learning_rate": 9.302435262558748e-06,
+      "loss": 3.2639,
+      "step": 57
+    },
+    {
+      "epoch": 0.2049469964664311,
+      "grad_norm": 3.8267316818237305,
+      "learning_rate": 8.954715367323468e-06,
+      "loss": 3.5431,
+      "step": 58
+    },
+    {
+      "epoch": 0.20848056537102475,
+      "grad_norm": 3.9242968559265137,
+      "learning_rate": 8.60826899039935e-06,
+      "loss": 3.1809,
+      "step": 59
+    },
+    {
+      "epoch": 0.21201413427561838,
+      "grad_norm": 3.4202167987823486,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 3.4313,
+      "step": 60
+    },
+    {
+      "epoch": 0.21554770318021202,
+      "grad_norm": 3.4609107971191406,
+      "learning_rate": 7.92088309182241e-06,
+      "loss": 3.0355,
+      "step": 61
+    },
+    {
+      "epoch": 0.21908127208480566,
+      "grad_norm": 3.4130520820617676,
+      "learning_rate": 7.580781044003324e-06,
+      "loss": 3.4006,
+      "step": 62
+    },
+    {
+      "epoch": 0.2226148409893993,
+      "grad_norm": 3.4137520790100098,
+      "learning_rate": 7.243626441830009e-06,
+      "loss": 3.4577,
+      "step": 63
+    },
+    {
+      "epoch": 0.2226148409893993,
+      "eval_loss": 3.1747097969055176,
+      "eval_runtime": 7.17,
+      "eval_samples_per_second": 33.333,
+      "eval_steps_per_second": 4.184,
+      "step": 63
+    },
+    {
+      "epoch": 0.22614840989399293,
+      "grad_norm": 3.42524790763855,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 3.074,
+      "step": 64
+    },
+    {
+      "epoch": 0.22968197879858657,
+      "grad_norm": 3.5621337890625,
+      "learning_rate": 6.579798566743314e-06,
+      "loss": 3.0764,
+      "step": 65
+    },
+    {
+      "epoch": 0.2332155477031802,
+      "grad_norm": 3.954556465148926,
+      "learning_rate": 6.25393406584088e-06,
+      "loss": 3.2832,
+      "step": 66
+    },
+    {
+      "epoch": 0.23674911660777384,
+      "grad_norm": 3.518817663192749,
+      "learning_rate": 5.932633569242e-06,
+      "loss": 3.0194,
+      "step": 67
+    },
+    {
+      "epoch": 0.24028268551236748,
+      "grad_norm": 3.8170769214630127,
+      "learning_rate": 5.616288532109225e-06,
+      "loss": 3.2752,
+      "step": 68
+    },
+    {
+      "epoch": 0.24381625441696114,
+      "grad_norm": 3.3504433631896973,
+      "learning_rate": 5.305284372141095e-06,
+      "loss": 3.2076,
+      "step": 69
+    },
+    {
+      "epoch": 0.24734982332155478,
+      "grad_norm": 3.452834129333496,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 3.356,
+      "step": 70
+    },
+    {
+      "epoch": 0.2508833922261484,
+      "grad_norm": 4.365915775299072,
+      "learning_rate": 4.700807357667953e-06,
+      "loss": 3.3366,
+      "step": 71
+    },
+    {
+      "epoch": 0.254416961130742,
+      "grad_norm": 3.3894336223602295,
+      "learning_rate": 4.408070965292534e-06,
+      "loss": 3.413,
+      "step": 72
+    },
+    {
+      "epoch": 0.254416961130742,
+      "eval_loss": 3.1335721015930176,
+      "eval_runtime": 7.1737,
+      "eval_samples_per_second": 33.316,
+      "eval_steps_per_second": 4.182,
+      "step": 72
+    },
+    {
+      "epoch": 0.2579505300353357,
+      "grad_norm": 3.383213996887207,
+      "learning_rate": 4.12214747707527e-06,
+      "loss": 3.1959,
+      "step": 73
+    },
+    {
+      "epoch": 0.26148409893992935,
+      "grad_norm": 3.5894997119903564,
+      "learning_rate": 3.8433852467434175e-06,
+      "loss": 3.3013,
+      "step": 74
+    },
+    {
+      "epoch": 0.26501766784452296,
+      "grad_norm": 3.3693082332611084,
+      "learning_rate": 3.5721239031346067e-06,
+      "loss": 3.1231,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4838612847820800.0,
+  "total_flos": 7257919271731200.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null