Training in progress, step 6, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "down_proj",
+    "up_proj",
     "o_proj",
     "q_proj",
+    "k_proj",
+    "down_proj",
     "gate_proj",
-    "up_proj",
-    "k_proj"
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f9deaefb906514604bb6873bca5a2a8c97c017312d4156325e0fd14270d4af1
+oid sha256:bef2f51ca79e45c8155c81c9572e626bda6dd5495183ab8ca37f6ea03c35eb2a
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5ad4b7618083a721ff31924e60ac3852e7e9960c460aafb49e5ebcdbaa98788
+oid sha256:3c1c66dcae0fedba5e29e93d51fbd63a1113afe98080f0666c082601d139fcec
 size 25986148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29425389f96c76b576bcff3abe69f0a48e741ce688d6737071ae45a2ad2d7584
+oid sha256:2cb24b3f3f4c4a67fab43264a5041d5eddbe696e430c47d0bfd9e5f90902b3a0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,16 +1,16 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0003022746164890803,
+  "epoch": 0.0006045492329781607,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.00010075820549636011,
-      "grad_norm": 8.359752932236722e+18,
+      "grad_norm": 6.578465480158216e+18,
       "learning_rate": 2e-05,
       "loss": 1.8654,
       "step": 1
@@ -18,32 +18,61 @@
     {
       "epoch": 0.00010075820549636011,
       "eval_loss": 1.7779617309570312,
-      "eval_runtime": 1454.9416,
-      "eval_samples_per_second": 2.872,
-      "eval_steps_per_second": 1.436,
+      "eval_runtime": 1454.0406,
+      "eval_samples_per_second": 2.874,
+      "eval_steps_per_second": 1.437,
       "step": 1
     },
     {
       "epoch": 0.00020151641099272022,
-      "grad_norm": 2.626370165041791e+18,
+      "grad_norm": 2.1462115130466632e+18,
       "learning_rate": 4e-05,
       "loss": 1.3359,
       "step": 2
     },
     {
       "epoch": 0.0003022746164890803,
-      "grad_norm": 3.249743505089626e+18,
+      "grad_norm": 2.517414610043142e+18,
       "learning_rate": 6e-05,
-      "loss": 1.3042,
+      "loss": 1.3138,
       "step": 3
     },
     {
       "epoch": 0.0003022746164890803,
-      "eval_loss": 1.7708849906921387,
-      "eval_runtime": 1454.6249,
-      "eval_samples_per_second": 2.873,
+      "eval_loss": 1.7785661220550537,
+      "eval_runtime": 1454.8386,
+      "eval_samples_per_second": 2.872,
       "eval_steps_per_second": 1.437,
       "step": 3
+    },
+    {
+      "epoch": 0.00040303282198544043,
+      "grad_norm": 7.439758018171896e+18,
+      "learning_rate": 8e-05,
+      "loss": 1.5352,
+      "step": 4
+    },
+    {
+      "epoch": 0.0005037910274818005,
+      "grad_norm": 3.50965568439006e+18,
+      "learning_rate": 0.0001,
+      "loss": 1.2199,
+      "step": 5
+    },
+    {
+      "epoch": 0.0006045492329781607,
+      "grad_norm": 5.017360729099993e+18,
+      "learning_rate": 0.00012,
+      "loss": 1.6428,
+      "step": 6
+    },
+    {
+      "epoch": 0.0006045492329781607,
+      "eval_loss": 1.799889326095581,
+      "eval_runtime": 1454.8745,
+      "eval_samples_per_second": 2.872,
+      "eval_steps_per_second": 1.437,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 617621263220736.0,
+  "total_flos": 1235242526441472.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58a3eb8d82e5fbac81f07720d857f56891a89c37b161f0eab5a75ef832506307
+oid sha256:b28660bfe89cc0538651f48cd70f7a481a8052384d78f5c68e3271d050811326
 size 6776