Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7651c9a3a7b0bb82d11f80a926ce7d44e989b1dd7f50e8b67c35ee30afb803db
+oid sha256:f6097bcaa7ebc4d5338f0c8291ea1c8ba9d8dc1728c6cd3ce1abc6b2496599da
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a96c2a8355ab4e4916cc29650a6e0cd0a86d6a65ec595fd7093a173d2f5d2d6
+oid sha256:ae733c3f0e030b67899bc7cfbf9af2c544ec06232139446de9a52425a6616306
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15ffd8689bfc9d36d10f4de88ee95f4060bd8e23db4bb3e43f2a175fdee90af5
+oid sha256:48b571a1cda1c18e0b76f3cd6c89bae53eb9d1241ef187c71a1c58bcd4925246
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f7e91af1a79d7676619e959cc4b5dde54a9e2ec825d24c1c34fe5387a27894f
+oid sha256:d914dc409ae93ac75985631a9974025ebaa397f621307eef226e7d6e1076a1f6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08661758336942399,
+  "epoch": 0.17323516673884798,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 4.417,
       "eval_steps_per_second": 2.209,
       "step": 25
+    },
+    {
+      "epoch": 0.09008228670420096,
+      "grad_norm": 30.413021087646484,
+      "learning_rate": 0.0001537299608346824,
+      "loss": 4.3897,
+      "step": 26
+    },
+    {
+      "epoch": 0.09354699003897791,
+      "grad_norm": 70.32632446289062,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 6.1758,
+      "step": 27
+    },
+    {
+      "epoch": 0.09701169337375487,
+      "grad_norm": 44.74322509765625,
+      "learning_rate": 0.00014617486132350343,
+      "loss": 5.2728,
+      "step": 28
+    },
+    {
+      "epoch": 0.10047639670853183,
+      "grad_norm": 44.46076965332031,
+      "learning_rate": 0.00014226182617406996,
+      "loss": 7.1594,
+      "step": 29
+    },
+    {
+      "epoch": 0.1039411000433088,
+      "grad_norm": 55.632720947265625,
+      "learning_rate": 0.000138268343236509,
+      "loss": 3.2506,
+      "step": 30
+    },
+    {
+      "epoch": 0.10740580337808575,
+      "grad_norm": 64.20110321044922,
+      "learning_rate": 0.00013420201433256689,
+      "loss": 4.082,
+      "step": 31
+    },
+    {
+      "epoch": 0.11087050671286271,
+      "grad_norm": 82.19364166259766,
+      "learning_rate": 0.00013007057995042732,
+      "loss": 5.7286,
+      "step": 32
+    },
+    {
+      "epoch": 0.11433521004763968,
+      "grad_norm": 25.911882400512695,
+      "learning_rate": 0.00012588190451025207,
+      "loss": 3.3962,
+      "step": 33
+    },
+    {
+      "epoch": 0.11779991338241663,
+      "grad_norm": 34.44158935546875,
+      "learning_rate": 0.00012164396139381029,
+      "loss": 4.11,
+      "step": 34
+    },
+    {
+      "epoch": 0.12126461671719359,
+      "grad_norm": 29.16976547241211,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 4.2445,
+      "step": 35
+    },
+    {
+      "epoch": 0.12472932005197054,
+      "grad_norm": 18.717464447021484,
+      "learning_rate": 0.00011305261922200519,
+      "loss": 3.1105,
+      "step": 36
+    },
+    {
+      "epoch": 0.1281940233867475,
+      "grad_norm": 12.39698314666748,
+      "learning_rate": 0.00010871557427476583,
+      "loss": 2.9836,
+      "step": 37
+    },
+    {
+      "epoch": 0.13165872672152448,
+      "grad_norm": 20.110858917236328,
+      "learning_rate": 0.00010436193873653361,
+      "loss": 4.8843,
+      "step": 38
+    },
+    {
+      "epoch": 0.13512343005630142,
+      "grad_norm": 22.39121437072754,
+      "learning_rate": 0.0001,
+      "loss": 3.7531,
+      "step": 39
+    },
+    {
+      "epoch": 0.1385881333910784,
+      "grad_norm": 12.983887672424316,
+      "learning_rate": 9.563806126346642e-05,
+      "loss": 2.8063,
+      "step": 40
+    },
+    {
+      "epoch": 0.14205283672585534,
+      "grad_norm": 12.021308898925781,
+      "learning_rate": 9.128442572523417e-05,
+      "loss": 1.8465,
+      "step": 41
+    },
+    {
+      "epoch": 0.1455175400606323,
+      "grad_norm": 32.44965744018555,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 4.7937,
+      "step": 42
+    },
+    {
+      "epoch": 0.14898224339540928,
+      "grad_norm": 16.291828155517578,
+      "learning_rate": 8.263518223330697e-05,
+      "loss": 4.0307,
+      "step": 43
+    },
+    {
+      "epoch": 0.15244694673018622,
+      "grad_norm": 12.486902236938477,
+      "learning_rate": 7.835603860618972e-05,
+      "loss": 3.1398,
+      "step": 44
+    },
+    {
+      "epoch": 0.1559116500649632,
+      "grad_norm": 20.737529754638672,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 2.7772,
+      "step": 45
+    },
+    {
+      "epoch": 0.15937635339974016,
+      "grad_norm": 17.130455017089844,
+      "learning_rate": 6.992942004957271e-05,
+      "loss": 2.7659,
+      "step": 46
+    },
+    {
+      "epoch": 0.1628410567345171,
+      "grad_norm": 33.27773666381836,
+      "learning_rate": 6.579798566743314e-05,
+      "loss": 4.4388,
+      "step": 47
+    },
+    {
+      "epoch": 0.16630576006929407,
+      "grad_norm": 16.671640396118164,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 5.4897,
+      "step": 48
+    },
+    {
+      "epoch": 0.16977046340407104,
+      "grad_norm": 32.55076599121094,
+      "learning_rate": 5.773817382593008e-05,
+      "loss": 5.7507,
+      "step": 49
+    },
+    {
+      "epoch": 0.17323516673884798,
+      "grad_norm": 24.630674362182617,
+      "learning_rate": 5.382513867649663e-05,
+      "loss": 4.7681,
+      "step": 50
+    },
+    {
+      "epoch": 0.17323516673884798,
+      "eval_loss": 0.4547581374645233,
+      "eval_runtime": 55.2618,
+      "eval_samples_per_second": 4.415,
+      "eval_steps_per_second": 2.208,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.347789697024e+16,
+  "total_flos": 1.2695579394048e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null